Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4698 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.4140. Min Act: -0.1700
Data Index: 432750 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.4140. Min Act: -0.1700
Data Index: 8158569 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.3827. Min Act: -0.1700
Data Index: 2764439 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.4140. Min Act: -0.1700
Data Index: 1579574 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.2890. Min Act: -0.1700
Data Index: 6829756 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.2265. Min Act: -0.1700
Data Index: 5332616 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.2577. Min Act: -0.1700
Data Index: 2666907 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.2265. Min Act: -0.1700
Data Index: 4197032 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.2577. Min Act: -0.1700
Data Index: 6051472 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.1327. Min Act: -0.1700
Data Index: 6135596 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.1327. Min Act: -0.1700
Data Index: 8271816 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.1327. Min Act: -0.1700
Data Index: 8636365 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.1327. Min Act: -0.1700
Data Index: 7770504 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.1015. Min Act: -0.1700
Data Index: 5693832 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.1015. Min Act: -0.1700
Data Index: 1526549 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0702. Min Act: -0.1700
Data Index: 3533983 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0702. Min Act: -0.1700
Data Index: 1882647 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.1015. Min Act: -0.1700
Data Index: 7038786 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0390. Min Act: -0.1700
Data Index: 1316689 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4140. Min Range: -6.4140
Max Act: 6.0390. Min Act: -0.1700
Data Index: 5019605 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19