Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3861 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2685. Min Range: -7.2685
Max Act: 7.2685. Min Act: -0.1700
Data Index: 3316031 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2685. Min Range: -7.2685
Max Act: 7.1122. Min Act: -0.1700
Data Index: 1184926 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2685. Min Range: -7.2685
Max Act: 7.0810. Min Act: -0.1700
Data Index: 4967235 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.9247. Min Act: -0.1700
Data Index: 6015599 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.9247. Min Act: -0.1700
Data Index: 7377016 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.9247. Min Act: -0.1700
Data Index: 4877114 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.8622. Min Act: -0.1700
Data Index: 1254214 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.8622. Min Act: -0.1700
Data Index: 5233692 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.7685. Min Act: -0.1700
Data Index: 3803423 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.7685. Min Act: -0.1700
Data Index: 283790 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.7372. Min Act: -0.1700
Data Index: 7577794 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.7372. Min Act: -0.1700
Data Index: 8692711 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.7372. Min Act: -0.1700
Data Index: 590357 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.7060. Min Act: -0.1700
Data Index: 6904900 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.7060. Min Act: -0.1700
Data Index: 259767 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.6747. Min Act: -0.1700
Data Index: 7383563 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.6747. Min Act: -0.1700
Data Index: 413235 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.6747. Min Act: -0.1700
Data Index: 8342725 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.6747. Min Act: -0.1700
Data Index: 7275457 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2685. Min Range: -7.2685
Max Act: 6.6747. Min Act: -0.1700
Data Index: 4738666 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19