Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4446 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.7008. Min Act: -0.1700
Data Index: 6637261 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.7008. Min Act: -0.1700
Data Index: 4824633 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.6383. Min Act: -0.1700
Data Index: 5024840 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.3883. Min Act: -0.1700
Data Index: 5133707 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.2633. Min Act: -0.1700
Data Index: 5169470 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.2008. Min Act: -0.1700
Data Index: 4013032 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.2008. Min Act: -0.1700
Data Index: 6241596 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.2008. Min Act: -0.1700
Data Index: 220676 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.1383. Min Act: -0.1700
Data Index: 2458778 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.1383. Min Act: -0.1700
Data Index: 1459043 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.0758. Min Act: -0.1700
Data Index: 3664635 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.0758. Min Act: -0.1700
Data Index: 7586461 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7008. Min Range: -10.7008
Max Act: 10.0758. Min Act: -0.1700
Data Index: 8108480 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7008. Min Range: -10.7008
Max Act: 9.9508. Min Act: -0.1700
Data Index: 7322354 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7008. Min Range: -10.7008
Max Act: 9.9508. Min Act: -0.1700
Data Index: 2285630 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7008. Min Range: -10.7008
Max Act: 9.8883. Min Act: -0.1700
Data Index: 4685823 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7008. Min Range: -10.7008
Max Act: 9.9508. Min Act: -0.1700
Data Index: 4172467 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7008. Min Range: -10.7008
Max Act: 9.8258. Min Act: -0.1700
Data Index: 2492739 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7008. Min Range: -10.7008
Max Act: 9.8883. Min Act: -0.1700
Data Index: 2379121 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7008. Min Range: -10.7008
Max Act: 9.7633. Min Act: -0.1700
Data Index: 5090652 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19