Rapid progress in deep learning over the past decade has led to important advances in human neuroscience. However, these advances have been largely concentrated in vision science, and have been slower to percolate out to more abstract topics of study, such as social cognition. In this talk, I will discuss three examples from my research which illustrate how artificial neural networks offer new insight into the social mind and brain. First, I will discuss how word embeddings facilitate cross-cultural social cognition research by allowing us to probe the meaning of mental state terms across countries, languages, and history. Second, I will discuss how neural networks can be used to model human social cognition, revealing how the conceptual structure of mental state representation can be derived from mental state dynamics. Third, I will discuss how deep convolutional neural networks can be used to automatically annotate socially relevant stimuli in naturalistic fMRI, allowing us to test a psychological theory of action representation. I will conclude by outlining promising avenues for future research at the intersection of social neuroscience and deep learning.