Merge pull request huggingface#286 from hendrycks/patch-1

Update activation function docstring

pytorch_pretrained_bert/modeling.py

@@ -114,6 +114,7 @@ def gelu(x):
     """Implementation of the gelu activation function.
         For information: OpenAI GPT's gelu is slightly different (and gives slightly different results):
         0.5 * x * (1 + torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3))))
+        Also see https://arxiv.org/abs/1606.08415
     """
     return x * 0.5 * (1.0 + torch.erf(x / math.sqrt(2.0)))