Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5725 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3298. Min Range: -10.3298
Max Act: 10.3298. Min Act: -0.1700
Data Index: 8485605 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3298. Min Range: -10.3298
Max Act: 10.2048. Min Act: -0.1700
Data Index: 1297748 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3298. Min Range: -10.3298
Max Act: 10.1423. Min Act: -0.1700
Data Index: 5518012 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3298. Min Range: -10.3298
Max Act: 10.0173. Min Act: -0.1700
Data Index: 6299464 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3298. Min Range: -10.3298
Max Act: 10.0173. Min Act: -0.1700
Data Index: 1985889 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.9548. Min Act: -0.1700
Data Index: 6392706 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.8298. Min Act: -0.1700
Data Index: 3546951 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.7048. Min Act: -0.1700
Data Index: 1380563 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.6423. Min Act: -0.1700
Data Index: 4702868 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.6423. Min Act: -0.1700
Data Index: 1882513 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.6423. Min Act: -0.1700
Data Index: 4135002 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.5798. Min Act: -0.1700
Data Index: 4962472 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.5173. Min Act: -0.1700
Data Index: 2994480 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.5173. Min Act: -0.1700
Data Index: 7495921 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.4548. Min Act: -0.1700
Data Index: 7212286 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.4548. Min Act: -0.1700
Data Index: 2864836 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.4548. Min Act: -0.1700
Data Index: 1425458 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.4548. Min Act: -0.1700
Data Index: 7126715 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.4548. Min Act: -0.1700
Data Index: 2232082 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3298. Min Range: -10.3298
Max Act: 9.4548. Min Act: -0.1700
Data Index: 2905127 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19