Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4634 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.9348. Min Act: -0.1700
Data Index: 5584314 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.6848. Min Act: -0.1700
Data Index: 5345271 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.6223. Min Act: -0.1700
Data Index: 5612870 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.6223. Min Act: -0.1700
Data Index: 5052013 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.5598. Min Act: -0.1700
Data Index: 2040564 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.5598. Min Act: -0.1700
Data Index: 5392480 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.4973. Min Act: -0.1700
Data Index: 8162933 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.4973. Min Act: -0.1700
Data Index: 3115472 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.3723. Min Act: -0.1700
Data Index: 923882 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.3723. Min Act: -0.1700
Data Index: 1338093 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.3723. Min Act: -0.1700
Data Index: 8672040 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.3723. Min Act: -0.1700
Data Index: 7531864 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.3723. Min Act: -0.1700
Data Index: 3961601 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.3098. Min Act: -0.1700
Data Index: 6231652 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.3098. Min Act: -0.1700
Data Index: 2771237 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.3098. Min Act: -0.1700
Data Index: 4746575 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.3098. Min Act: -0.1700
Data Index: 4935844 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.3098. Min Act: -0.1700
Data Index: 2957760 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.2473. Min Act: -0.1700
Data Index: 919492 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9348. Min Range: -8.9348
Max Act: 8.2473. Min Act: -0.1700
Data Index: 7919865 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19