Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.9872. Min Act: -0.1700
Data Index: 1355477 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.9448. Min Act: -0.1700
Data Index: 4769597 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.9448. Min Act: -0.1700
Data Index: 6812903 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.9193. Min Act: -0.1699
Data Index: 1229735 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.9108. Min Act: -0.1700
Data Index: 8591641 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.9278. Min Act: -0.1700
Data Index: 8518558 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.9193. Min Act: -0.1700
Data Index: 658414 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8852. Min Act: -0.1700
Data Index: 8665082 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8852. Min Act: -0.1700
Data Index: 2433856 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8852. Min Act: -0.1697
Data Index: 5142384 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8852. Min Act: -0.1700
Data Index: 2923106 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8766. Min Act: -0.1700
Data Index: 4494311 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8766. Min Act: -0.1656
Data Index: 8015816 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8681. Min Act: -0.1700
Data Index: 8197868 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8681. Min Act: -0.1700
Data Index: 2576823 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8681. Min Act: -0.1700
Data Index: 2395070 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8766. Min Act: -0.1700
Data Index: 6923132 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8681. Min Act: -0.1700
Data Index: 7733919 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8681. Min Act: -0.1700
Data Index: 837115 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9872. Min Range: -1.9872
Max Act: 1.8595. Min Act: -0.1700
Data Index: 1824428 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19