Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2356 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.9040. Min Act: -0.1700
Data Index: 4567891 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.9353. Min Act: -0.1700
Data Index: 548270 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.8415. Min Act: -0.1700
Data Index: 5191553 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.8103. Min Act: -0.1700
Data Index: 7209889 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.8103. Min Act: -0.1700
Data Index: 5888209 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.8103. Min Act: -0.1700
Data Index: 813761 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.7790. Min Act: -0.1700
Data Index: 1142190 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.7478. Min Act: -0.1700
Data Index: 924748 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.6540. Min Act: -0.1700
Data Index: 7397049 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.6540. Min Act: -0.1700
Data Index: 7016164 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.7165. Min Act: -0.1700
Data Index: 988057 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.6228. Min Act: -0.1700
Data Index: 4972725 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.6228. Min Act: -0.1700
Data Index: 2170004 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.6228. Min Act: -0.1700
Data Index: 3565716 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.6228. Min Act: -0.1700
Data Index: 1120774 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.6228. Min Act: -0.1700
Data Index: 3600760 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.6228. Min Act: -0.1700
Data Index: 3577548 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.5915. Min Act: -0.1700
Data Index: 1181 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.5603. Min Act: -0.1700
Data Index: 2903591 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9353. Min Range: -4.9353
Max Act: 4.5915. Min Act: -0.1700
Data Index: 5514617 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19