Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.3084. Min Act: -0.1700
Data Index: 6157358 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.1985. Min Act: -0.1700
Data Index: 1893006 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.1670. Min Act: -0.1700
Data Index: 3121614 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.1355. Min Act: -0.1700
Data Index: 3034164 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.1198. Min Act: -0.1700
Data Index: 5091356 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0882. Min Act: -0.1700
Data Index: 2393770 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0882. Min Act: -0.1700
Data Index: 4332616 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0725. Min Act: -0.1700
Data Index: 330236 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0725. Min Act: -0.1700
Data Index: 1380780 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0567. Min Act: -0.1700
Data Index: 7875406 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0409. Min Act: -0.1700
Data Index: 8156775 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0409. Min Act: -0.1700
Data Index: 8076200 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0251. Min Act: -0.1700
Data Index: 8503692 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0251. Min Act: -0.1700
Data Index: 1567885 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0093. Min Act: -0.1700
Data Index: 8100722 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0093. Min Act: -0.1700
Data Index: 5809856 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0093. Min Act: -0.1700
Data Index: 789429 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0093. Min Act: -0.1700
Data Index: 4990610 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3084. Min Range: -3.3084
Max Act: 2.9777. Min Act: -0.1700
Data Index: 4526433 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3084. Min Range: -3.3084
Max Act: 3.0251. Min Act: -0.1700
Data Index: 5353866 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19