Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3951 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1451. Min Range: -7.1451
Max Act: 7.1451. Min Act: -0.1700
Data Index: 4232866 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.8951. Min Act: -0.1700
Data Index: 5733006 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.8326. Min Act: -0.1700
Data Index: 8480291 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.8326. Min Act: -0.1700
Data Index: 7353391 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.8014. Min Act: -0.1700
Data Index: 5381854 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.7701. Min Act: -0.1700
Data Index: 4633056 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.7389. Min Act: -0.1700
Data Index: 2241816 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.7389. Min Act: -0.1700
Data Index: 3178002 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.7076. Min Act: -0.1700
Data Index: 532911 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.7076. Min Act: -0.1700
Data Index: 6253181 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.7076. Min Act: -0.1700
Data Index: 7078320 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.5826. Min Act: -0.1700
Data Index: 2539322 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.5826. Min Act: -0.1700
Data Index: 2420536 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.5514. Min Act: -0.1700
Data Index: 959729 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.5826. Min Act: -0.1700
Data Index: 6538730 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.4889. Min Act: -0.1700
Data Index: 5095696 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.4889. Min Act: -0.1700
Data Index: 4199291 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.4889. Min Act: -0.1700
Data Index: 2808531 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.4264. Min Act: -0.1700
Data Index: 8300522 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1451. Min Range: -7.1451
Max Act: 6.4576. Min Act: -0.1700
Data Index: 7878584 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19