Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3180 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.2252. Min Act: -0.1700
Data Index: 3040745 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.1315. Min Act: -0.1700
Data Index: 8000981 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.1627. Min Act: -0.1700
Data Index: 5034045 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.1315. Min Act: -0.1700
Data Index: 1121678 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0689. Min Act: -0.1700
Data Index: 4199237 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.1002. Min Act: -0.1700
Data Index: 58029 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.1002. Min Act: -0.1700
Data Index: 8073540 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.1002. Min Act: -0.1700
Data Index: 8315993 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.1002. Min Act: -0.1700
Data Index: 6547479 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0689. Min Act: -0.1700
Data Index: 1153179 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0689. Min Act: -0.1700
Data Index: 320870 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0689. Min Act: -0.1700
Data Index: 7251288 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0377. Min Act: -0.1700
Data Index: 990659 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0377. Min Act: -0.1700
Data Index: 5121767 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0377. Min Act: -0.1700
Data Index: 7529701 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0689. Min Act: -0.1700
Data Index: 7289145 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0377. Min Act: -0.1700
Data Index: 7243563 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0377. Min Act: -0.1700
Data Index: 6693314 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0064. Min Act: -0.1700
Data Index: 955841 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2252. Min Range: -4.2252
Max Act: 4.0377. Min Act: -0.1700
Data Index: 5457349 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19