When living in urban habitats, ‘urban adapter’ species often show greater aggression toward conspecifics, yet we do not understand the mechanisms underlying this behavioral shift. The neuroendocrine system regulates socio-sexual behaviors including aggression and thus could mediate behavioral responses to urbanization. Indeed, urban male song sparrows (Melospiza melodia), which are more territorially aggressive, also have greater abundance of the neuropeptide arginine vasotocin (AVT) in nodes of the brain social behavior network. Higher abundance of AVT could reflect long-term synthesis that underlies baseline territoriality or short-term changes that regulate aggression in response to social challenge. To begin to resolve the timeframe over which the AVT system contributes to habitat differences in aggression we used immediate early gene co-expression as a measure of the activation of AVT neurons. We compared Fos induction in AVT-immunoreactive neurons of the bed nucleus of the stria terminalis (BSTm) and paraventricular nucleus of the hypothalamus (PVN) between urban and rural male song sparrows in response to a short (< 5 min.) or long (> 30 min.) song playback to simulate territorial intrusion by another male. We found that urban males had a higher proportion of Fos-positive AVT neurons in both brain regions compared to rural males, regardless of the duration of song playback. Our results suggest that AVT neurons remain activated in urban males, independently of the duration of social challenge. These findings that Fos induction in AVT neurons differs between rural and urban male song sparrows further implicate this system in regulating behavioral responses to urbanization.