Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 556 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3348. Min Range: -4.3348
Max Act: 4.3348. Min Act: -0.1700
Data Index: 139882 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3348. Min Range: -4.3348
Max Act: 4.2723. Min Act: -0.1700
Data Index: 1596951 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3348. Min Range: -4.3348
Max Act: 4.2411. Min Act: -0.1700
Data Index: 7460209 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3348. Min Range: -4.3348
Max Act: 4.1786. Min Act: -0.1700
Data Index: 8471476 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3348. Min Range: -4.3348
Max Act: 4.1473. Min Act: -0.1700
Data Index: 2761563 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3348. Min Range: -4.3348
Max Act: 4.1161. Min Act: -0.1700
Data Index: 4697454 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3348. Min Range: -4.3348
Max Act: 4.0848. Min Act: -0.1700
Data Index: 7016602 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3348. Min Range: -4.3348
Max Act: 4.0536. Min Act: -0.1700
Data Index: 4307679 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3348. Min Range: -4.3348
Max Act: 4.0536. Min Act: -0.1700
Data Index: 3230488 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3348. Min Range: -4.3348
Max Act: 4.0223. Min Act: -0.1700
Data Index: 2541836 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3348. Min Range: -4.3348
Max Act: 3.9910. Min Act: -0.1700
Data Index: 312727 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3348. Min Range: -4.3348
Max Act: 3.9910. Min Act: -0.1700
Data Index: 350530 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3348. Min Range: -4.3348
Max Act: 3.9910. Min Act: -0.1700
Data Index: 2876543 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3348. Min Range: -4.3348
Max Act: 3.9910. Min Act: -0.1700
Data Index: 1869256 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3348. Min Range: -4.3348
Max Act: 3.9598. Min Act: -0.1700
Data Index: 3971759 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3348. Min Range: -4.3348
Max Act: 3.9598. Min Act: -0.1700
Data Index: 1738376 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3348. Min Range: -4.3348
Max Act: 3.9598. Min Act: -0.1700
Data Index: 5855357 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3348. Min Range: -4.3348
Max Act: 3.9598. Min Act: -0.1700
Data Index: 5417747 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3348. Min Range: -4.3348
Max Act: 3.9598. Min Act: -0.1700
Data Index: 8190130 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3348. Min Range: -4.3348
Max Act: 3.9285. Min Act: -0.1700
Data Index: 302911 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19