Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4521 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3598. Min Range: -8.3598
Max Act: 8.3598. Min Act: -0.1700
Data Index: 4886954 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3598. Min Range: -8.3598
Max Act: 8.1098. Min Act: -0.1700
Data Index: 2873867 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.8598. Min Act: -0.1700
Data Index: 4831049 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.8598. Min Act: -0.1700
Data Index: 4562642 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.8598. Min Act: -0.1700
Data Index: 6385974 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.6723. Min Act: -0.1700
Data Index: 987438 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.6723. Min Act: -0.1700
Data Index: 8326714 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.6098. Min Act: -0.1700
Data Index: 8357504 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.6098. Min Act: -0.1700
Data Index: 6676447 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.6098. Min Act: -0.1700
Data Index: 3645029 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.5473. Min Act: -0.1700
Data Index: 6132318 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.5473. Min Act: -0.1700
Data Index: 2384554 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.3910. Min Act: -0.1700
Data Index: 639521 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.3910. Min Act: -0.1700
Data Index: 8461229 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.3910. Min Act: -0.1700
Data Index: 72229 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.3598. Min Act: -0.1700
Data Index: 4860684 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.3285. Min Act: -0.1700
Data Index: 5482964 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.3598. Min Act: -0.1700
Data Index: 3435407 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.3285. Min Act: -0.1700
Data Index: 3926493 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3598. Min Range: -8.3598
Max Act: 7.2660. Min Act: -0.1700
Data Index: 444746 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19