Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4927. Min Range: -6.4927
Max Act: 6.4927. Min Act: -0.1700
Data Index: 905471 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4927. Min Range: -6.4927
Max Act: 6.3052. Min Act: -0.1700
Data Index: 796706 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4927. Min Range: -6.4927
Max Act: 6.2739. Min Act: -0.1700
Data Index: 89663 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4927. Min Range: -6.4927
Max Act: 6.1177. Min Act: -0.1700
Data Index: 4156222 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4927. Min Range: -6.4927
Max Act: 6.1177. Min Act: -0.1700
Data Index: 71819 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4927. Min Range: -6.4927
Max Act: 6.0552. Min Act: -0.1700
Data Index: 1387107 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4927. Min Range: -6.4927
Max Act: 6.0552. Min Act: -0.1700
Data Index: 894898 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.9614. Min Act: -0.1700
Data Index: 5891564 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.9302. Min Act: -0.1700
Data Index: 7402849 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.8989. Min Act: -0.1700
Data Index: 7700398 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.8677. Min Act: -0.1700
Data Index: 1004165 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.8677. Min Act: -0.1700
Data Index: 5289255 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.8677. Min Act: -0.1700
Data Index: 4964091 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.8364. Min Act: -0.1700
Data Index: 7874049 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.8364. Min Act: -0.1700
Data Index: 5357956 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.8364. Min Act: -0.1700
Data Index: 4078991 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.8677. Min Act: -0.1700
Data Index: 1033904 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.8364. Min Act: -0.1700
Data Index: 816214 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.8052. Min Act: -0.1700
Data Index: 1632891 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4927. Min Range: -6.4927
Max Act: 5.8052. Min Act: -0.1700
Data Index: 6649012 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19