Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.2129. Min Act: -0.1700
Data Index: 6486718 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.1504. Min Act: -0.1700
Data Index: 6537177 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.1504. Min Act: -0.1700
Data Index: 4688310 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.1192. Min Act: -0.1700
Data Index: 7067865 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.1192. Min Act: -0.1700
Data Index: 1154686 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0567. Min Act: -0.1700
Data Index: 1047640 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0879. Min Act: -0.1700
Data Index: 1569608 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0879. Min Act: -0.1700
Data Index: 3686546 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0879. Min Act: -0.1700
Data Index: 4985707 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0567. Min Act: -0.1700
Data Index: 1474779 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0567. Min Act: -0.1700
Data Index: 4854412 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0567. Min Act: -0.1700
Data Index: 274253 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0567. Min Act: -0.1700
Data Index: 520106 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0567. Min Act: -0.1700
Data Index: 6729365 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0567. Min Act: -0.1700
Data Index: 842848 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0567. Min Act: -0.1700
Data Index: 5815535 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0254. Min Act: -0.1700
Data Index: 4957792 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0254. Min Act: -0.1700
Data Index: 1866814 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0254. Min Act: -0.1700
Data Index: 3926459 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2129. Min Range: -4.2129
Max Act: 4.0567. Min Act: -0.1700
Data Index: 6138817 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19