Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2695 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.9976. Min Act: -0.1700
Data Index: 5321996 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.7476. Min Act: -0.1700
Data Index: 6396396 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.6851. Min Act: -0.1700
Data Index: 1475623 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.5914. Min Act: -0.1700
Data Index: 4889107 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.5914. Min Act: -0.1700
Data Index: 5667477 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.4976. Min Act: -0.1700
Data Index: 7171693 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.4351. Min Act: -0.1700
Data Index: 6772459 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.4039. Min Act: -0.1700
Data Index: 1867051 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.3414. Min Act: -0.1700
Data Index: 5237758 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.4039. Min Act: -0.1700
Data Index: 6584494 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.3726. Min Act: -0.1700
Data Index: 8033624 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.3414. Min Act: -0.1700
Data Index: 219273 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.3414. Min Act: -0.1700
Data Index: 7766479 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.3414. Min Act: -0.1700
Data Index: 7804780 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.3101. Min Act: -0.1700
Data Index: 5210196 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.3101. Min Act: -0.1700
Data Index: 154370 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.3101. Min Act: -0.1700
Data Index: 3372887 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.2789. Min Act: -0.1700
Data Index: 1881979 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.2789. Min Act: -0.1700
Data Index: 760104 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9976. Min Range: -5.9976
Max Act: 5.2789. Min Act: -0.1700
Data Index: 6240068 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19