Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.8698. Min Act: -0.1700
Data Index: 5824948 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.7448. Min Act: -0.1700
Data Index: 6385572 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.5885. Min Act: -0.1700
Data Index: 8517439 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.5885. Min Act: -0.1700
Data Index: 7575480 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.5885. Min Act: -0.1700
Data Index: 400269 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.5260. Min Act: -0.1700
Data Index: 126669 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.5260. Min Act: -0.1700
Data Index: 7398921 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.4948. Min Act: -0.1700
Data Index: 4961623 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.4323. Min Act: -0.1700
Data Index: 3383173 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.4323. Min Act: -0.1700
Data Index: 3752143 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.4010. Min Act: -0.1700
Data Index: 715692 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.4010. Min Act: -0.1700
Data Index: 1324222 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.3698. Min Act: -0.1700
Data Index: 3105500 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.4010. Min Act: -0.1700
Data Index: 2020602 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.3385. Min Act: -0.1700
Data Index: 5105364 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.3073. Min Act: -0.1700
Data Index: 5342318 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.3385. Min Act: -0.1700
Data Index: 6011359 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.3073. Min Act: -0.1700
Data Index: 5786500 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.3073. Min Act: -0.1700
Data Index: 2521758 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8698. Min Range: -5.8698
Max Act: 5.3073. Min Act: -0.1700
Data Index: 737782 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19