Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5004 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.2876. Min Act: -0.1700
Data Index: 77504 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.2876. Min Act: -0.1700
Data Index: 574421 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.2563. Min Act: -0.1700
Data Index: 1468642 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.2563. Min Act: -0.1700
Data Index: 2094041 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.2251. Min Act: -0.1700
Data Index: 8035800 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.1938. Min Act: -0.1700
Data Index: 5664773 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.1313. Min Act: -0.1700
Data Index: 5927605 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.1626. Min Act: -0.1700
Data Index: 7202547 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.1626. Min Act: -0.1700
Data Index: 6926334 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.1313. Min Act: -0.1700
Data Index: 4118206 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.1313. Min Act: -0.1700
Data Index: 3811351 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.1001. Min Act: -0.1700
Data Index: 3848769 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.1001. Min Act: -0.1700
Data Index: 918466 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.0376. Min Act: -0.1700
Data Index: 2147683 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.0376. Min Act: -0.1700
Data Index: 2709943 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.0376. Min Act: -0.1700
Data Index: 7014439 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.0376. Min Act: -0.1700
Data Index: 6882453 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.0688. Min Act: -0.1700
Data Index: 2085480 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.0688. Min Act: -0.1700
Data Index: 3050833 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2876. Min Range: -5.2876
Max Act: 5.0376. Min Act: -0.1700
Data Index: 6599965 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19