Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2682. Min Act: -0.1700
Data Index: 2151177 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2057. Min Act: -0.1700
Data Index: 4521876 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2057. Min Act: -0.1700
Data Index: 682313 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2057. Min Act: -0.1700
Data Index: 2960304 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1745. Min Act: -0.1700
Data Index: 2198089 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1745. Min Act: -0.1700
Data Index: 1207059 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1432. Min Act: -0.1700
Data Index: 4369105 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 405368 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 2126344 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 4241906 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 7833000 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 2979659 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 2451743 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 4843708 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 1869974 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0807. Min Act: -0.1700
Data Index: 5810049 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0807. Min Act: -0.1700
Data Index: 6284229 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0807. Min Act: -0.1700
Data Index: 6400464 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0807. Min Act: -0.1700
Data Index: 5240519 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1120. Min Act: -0.1700
Data Index: 2261079 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19