Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.5727. Min Act: -0.1700
Data Index: 1547998 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.5102. Min Act: -0.1700
Data Index: 3622581 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.5102. Min Act: -0.1700
Data Index: 2309897 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.4477. Min Act: -0.1700
Data Index: 5468143 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.3227. Min Act: -0.1700
Data Index: 5940918 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.2602. Min Act: -0.1700
Data Index: 1141336 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.2602. Min Act: -0.1700
Data Index: 56945 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.2602. Min Act: -0.1700
Data Index: 5900788 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.0727. Min Act: -0.1700
Data Index: 7436256 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.0727. Min Act: -0.1700
Data Index: 3871603 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.0727. Min Act: -0.1700
Data Index: 6918952 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5727. Min Range: -9.5727
Max Act: 9.0102. Min Act: -0.1700
Data Index: 7509177 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5727. Min Range: -9.5727
Max Act: 8.9477. Min Act: -0.1700
Data Index: 4020426 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5727. Min Range: -9.5727
Max Act: 8.9477. Min Act: -0.1700
Data Index: 3683121 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5727. Min Range: -9.5727
Max Act: 8.8852. Min Act: -0.1700
Data Index: 3291575 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5727. Min Range: -9.5727
Max Act: 8.8227. Min Act: -0.1700
Data Index: 577083 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5727. Min Range: -9.5727
Max Act: 8.8227. Min Act: -0.1700
Data Index: 1872404 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5727. Min Range: -9.5727
Max Act: 8.8227. Min Act: -0.1700
Data Index: 839273 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5727. Min Range: -9.5727
Max Act: 8.7602. Min Act: -0.1700
Data Index: 763409 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5727. Min Range: -9.5727
Max Act: 8.7602. Min Act: -0.1700
Data Index: 865213 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19