Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2933 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.8321. Min Act: -0.1700
Data Index: 743528 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.7071. Min Act: -0.1700
Data Index: 5854668 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.7071. Min Act: -0.1700
Data Index: 520794 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.7384. Min Act: -0.1700
Data Index: 8772235 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.6759. Min Act: -0.1700
Data Index: 637993 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.6446. Min Act: -0.1700
Data Index: 1377142 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.6134. Min Act: -0.1700
Data Index: 445005 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.6134. Min Act: -0.1700
Data Index: 1087630 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.5509. Min Act: -0.1700
Data Index: 4332862 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.5509. Min Act: -0.1700
Data Index: 2187426 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.5196. Min Act: -0.1700
Data Index: 7622744 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.5196. Min Act: -0.1700
Data Index: 3429586 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.5196. Min Act: -0.1700
Data Index: 648189 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.5196. Min Act: -0.1700
Data Index: 2989469 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.4884. Min Act: -0.1700
Data Index: 2862780 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.4571. Min Act: -0.1700
Data Index: 8572581 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.4571. Min Act: -0.1700
Data Index: 3853450 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.4571. Min Act: -0.1700
Data Index: 8191280 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.4571. Min Act: -0.1700
Data Index: 2225908 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8321. Min Range: -6.8321
Max Act: 6.4571. Min Act: -0.1700
Data Index: 2557930 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19