Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1112. Min Range: -6.1112
Max Act: 6.1112. Min Act: -0.1700
Data Index: 2502037 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.7674. Min Act: -0.1700
Data Index: 5093746 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.7362. Min Act: -0.1700
Data Index: 2859808 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.7362. Min Act: -0.1700
Data Index: 2504794 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.7362. Min Act: -0.1700
Data Index: 1960781 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.6737. Min Act: -0.1700
Data Index: 5083134 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.6737. Min Act: -0.1700
Data Index: 4860599 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.6424. Min Act: -0.1700
Data Index: 2176208 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.6424. Min Act: -0.1700
Data Index: 1684928 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.6112. Min Act: -0.1700
Data Index: 2569816 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.5799. Min Act: -0.1700
Data Index: 5373124 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.5487. Min Act: -0.1700
Data Index: 8359004 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.5487. Min Act: -0.1700
Data Index: 413994 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.5487. Min Act: -0.1700
Data Index: 29807 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.5174. Min Act: -0.1700
Data Index: 6668633 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.5174. Min Act: -0.1700
Data Index: 1363278 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.5174. Min Act: -0.1700
Data Index: 8054297 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.4549. Min Act: -0.1700
Data Index: 7159944 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.4549. Min Act: -0.1700
Data Index: 5373125 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1112. Min Range: -6.1112
Max Act: 5.4237. Min Act: -0.1700
Data Index: 7374496 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19