Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4155 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.4288. Min Act: -0.1700
Data Index: 6814158 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.3350. Min Act: -0.1700
Data Index: 7925398 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.3038. Min Act: -0.1700
Data Index: 25388 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2725. Min Act: -0.1700
Data Index: 7488066 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2725. Min Act: -0.1700
Data Index: 5906300 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2725. Min Act: -0.1700
Data Index: 1977926 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2413. Min Act: -0.1700
Data Index: 68379 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2413. Min Act: -0.1700
Data Index: 6418272 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2413. Min Act: -0.1700
Data Index: 4099365 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2413. Min Act: -0.1700
Data Index: 5889897 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2413. Min Act: -0.1700
Data Index: 4877555 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2413. Min Act: -0.1700
Data Index: 8578040 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2413. Min Act: -0.1700
Data Index: 7704589 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2413. Min Act: -0.1700
Data Index: 460607 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2413. Min Act: -0.1700
Data Index: 4805972 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2413. Min Act: -0.1700
Data Index: 261524 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2100. Min Act: -0.1700
Data Index: 2215966 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2100. Min Act: -0.1700
Data Index: 5015518 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2100. Min Act: -0.1700
Data Index: 524120 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4288. Min Range: -4.4288
Max Act: 4.2100. Min Act: -0.1700
Data Index: 843360 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19