diff --git a/dalle2_pytorch/dalle2_pytorch.py b/dalle2_pytorch/dalle2_pytorch.py
index 6cf8ac7..17d7924 100644
--- a/dalle2_pytorch/dalle2_pytorch.py
+++ b/dalle2_pytorch/dalle2_pytorch.py
@@ -599,7 +599,7 @@ class CausalTransformer(nn.Module):
         dim_head = 64,
         heads = 8,
         ff_mult = 4,
-        norm_out = False,
+        norm_out = True,
         attn_dropout = 0.,
         ff_dropout = 0.,
         final_proj = True
diff --git a/setup.py b/setup.py
index d153108..68367dc 100644
--- a/setup.py
+++ b/setup.py
@@ -10,7 +10,7 @@ setup(
       'dream = dalle2_pytorch.cli:dream'
     ],
   },
-  version = '0.0.91',
+  version = '0.0.92',
   license='MIT',
   description = 'DALL-E 2',
   author = 'Phil Wang',