Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3615 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.5367. Min Act: -0.1700
Data Index: 2230650 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.1304. Min Act: -0.1700
Data Index: 7281039 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.0992. Min Act: -0.1700
Data Index: 1592167 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.0367. Min Act: -0.1700
Data Index: 5951172 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.0054. Min Act: -0.1700
Data Index: 4148332 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.0054. Min Act: -0.1700
Data Index: 922607 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5367. Min Range: -6.5367
Max Act: 6.0054. Min Act: -0.1700
Data Index: 1104720 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9742. Min Act: -0.1700
Data Index: 5105130 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9429. Min Act: -0.1700
Data Index: 8689659 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9429. Min Act: -0.1700
Data Index: 3057707 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9429. Min Act: -0.1700
Data Index: 969194 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9429. Min Act: -0.1700
Data Index: 6049983 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9117. Min Act: -0.1700
Data Index: 3256574 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9117. Min Act: -0.1700
Data Index: 7605173 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9117. Min Act: -0.1700
Data Index: 4812181 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.9117. Min Act: -0.1700
Data Index: 7602565 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.8492. Min Act: -0.1700
Data Index: 8539981 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.8804. Min Act: -0.1700
Data Index: 4442651 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.8804. Min Act: -0.1700
Data Index: 3294430 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5367. Min Range: -6.5367
Max Act: 5.8804. Min Act: -0.1700
Data Index: 2386589 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19