Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1958 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.7867. Min Act: -0.1700
Data Index: 6125679 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.0992. Min Act: -0.1700
Data Index: 38987 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.9430. Min Act: -0.1700
Data Index: 5447519 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.8492. Min Act: -0.1700
Data Index: 7298369 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.8805. Min Act: -0.1700
Data Index: 4249065 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.8180. Min Act: -0.1700
Data Index: 5695255 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.7867. Min Act: -0.1700
Data Index: 4480538 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.7555. Min Act: -0.1700
Data Index: 527591 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.6930. Min Act: -0.1700
Data Index: 5852630 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.6930. Min Act: -0.1700
Data Index: 1710453 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.6617. Min Act: -0.1700
Data Index: 5651052 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.6617. Min Act: -0.1700
Data Index: 452842 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.6617. Min Act: -0.1700
Data Index: 1515537 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.6617. Min Act: -0.1700
Data Index: 7642709 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.5680. Min Act: -0.1700
Data Index: 6262795 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.5055. Min Act: -0.1700
Data Index: 4864153 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.5055. Min Act: -0.1700
Data Index: 3725472 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.5367. Min Act: -0.1700
Data Index: 7960373 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.4742. Min Act: -0.1700
Data Index: 353594 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7867. Min Range: -7.7867
Max Act: 6.4742. Min Act: -0.1700
Data Index: 4489753 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19