Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4720 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4628. Min Range: -9.4628
Max Act: 9.4628. Min Act: -0.1700
Data Index: 6843044 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4628. Min Range: -9.4628
Max Act: 8.0878. Min Act: -0.1700
Data Index: 4571164 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4628. Min Range: -9.4628
Max Act: 8.0566. Min Act: -0.1700
Data Index: 7667913 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4628. Min Range: -9.4628
Max Act: 8.0566. Min Act: -0.1700
Data Index: 4949883 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.6816. Min Act: -0.1700
Data Index: 8035510 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.6503. Min Act: -0.1700
Data Index: 8107848 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.6503. Min Act: -0.1700
Data Index: 68721 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.5566. Min Act: -0.1700
Data Index: 3873146 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.5878. Min Act: -0.1700
Data Index: 1684300 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.5566. Min Act: -0.1700
Data Index: 7008836 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.4941. Min Act: -0.1700
Data Index: 8549204 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.4941. Min Act: -0.1700
Data Index: 2633033 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.4941. Min Act: -0.1700
Data Index: 7411195 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.4628. Min Act: -0.1700
Data Index: 716239 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.3691. Min Act: -0.1700
Data Index: 2000325 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.4003. Min Act: -0.1700
Data Index: 7667914 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.4003. Min Act: -0.1700
Data Index: 4959427 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.3691. Min Act: -0.1700
Data Index: 4911633 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.3378. Min Act: -0.1700
Data Index: 4849694 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4628. Min Range: -9.4628
Max Act: 7.3691. Min Act: -0.1700
Data Index: 4911632 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19