Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3897 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.8224. Min Act: -0.1700
Data Index: 4788803 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.7912. Min Act: -0.1700
Data Index: 7828737 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.7287. Min Act: -0.1700
Data Index: 2554779 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.5412. Min Act: -0.1700
Data Index: 3466833 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.5412. Min Act: -0.1700
Data Index: 4884938 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.5099. Min Act: -0.1700
Data Index: 5592970 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.5099. Min Act: -0.1700
Data Index: 2885242 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.4787. Min Act: -0.1700
Data Index: 6126431 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.4787. Min Act: -0.1700
Data Index: 1105533 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.4474. Min Act: -0.1700
Data Index: 4627827 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.4162. Min Act: -0.1700
Data Index: 926519 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.4162. Min Act: -0.1700
Data Index: 8322926 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.4162. Min Act: -0.1700
Data Index: 150729 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.3849. Min Act: -0.1700
Data Index: 7108285 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.3849. Min Act: -0.1700
Data Index: 4788804 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.3849. Min Act: -0.1700
Data Index: 4019125 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.3849. Min Act: -0.1700
Data Index: 7419873 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.3537. Min Act: -0.1700
Data Index: 6420635 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.3537. Min Act: -0.1700
Data Index: 2437357 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8224. Min Range: -5.8224
Max Act: 5.3224. Min Act: -0.1700
Data Index: 913453 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19