Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4395 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8247. Min Range: -8.8247
Max Act: 8.8247. Min Act: -0.1700
Data Index: 3714791 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8247. Min Range: -8.8247
Max Act: 8.1997. Min Act: -0.1700
Data Index: 4524982 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.9184. Min Act: -0.1700
Data Index: 7019839 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.8247. Min Act: -0.1700
Data Index: 4589340 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.8559. Min Act: -0.1700
Data Index: 621230 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.7622. Min Act: -0.1700
Data Index: 7018444 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.7309. Min Act: -0.1700
Data Index: 1566903 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.7309. Min Act: -0.1700
Data Index: 5810454 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.6684. Min Act: -0.1700
Data Index: 5871148 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.6997. Min Act: -0.1700
Data Index: 7868728 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.6997. Min Act: -0.1700
Data Index: 5871147 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.6372. Min Act: -0.1700
Data Index: 371420 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.6684. Min Act: -0.1700
Data Index: 6599425 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.6059. Min Act: -0.1700
Data Index: 4507557 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.6372. Min Act: -0.1700
Data Index: 1625085 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.6059. Min Act: -0.1700
Data Index: 5139351 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.5747. Min Act: -0.1700
Data Index: 3338899 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.5747. Min Act: -0.1700
Data Index: 3982157 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.5122. Min Act: -0.1700
Data Index: 1841191 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8247. Min Range: -8.8247
Max Act: 7.5122. Min Act: -0.1700
Data Index: 8742236 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19