Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 773 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4066. Min Range: -6.4066
Max Act: 6.4066. Min Act: -0.1700
Data Index: 5767189 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.9066. Min Act: -0.1700
Data Index: 6675635 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.9066. Min Act: -0.1700
Data Index: 2732743 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.9378. Min Act: -0.1700
Data Index: 1028847 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.8753. Min Act: -0.1700
Data Index: 1992630 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.7816. Min Act: -0.1700
Data Index: 198423 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.7816. Min Act: -0.1700
Data Index: 6181638 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.7503. Min Act: -0.1700
Data Index: 1736200 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.7503. Min Act: -0.1700
Data Index: 2056977 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.7503. Min Act: -0.1700
Data Index: 3930747 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.6878. Min Act: -0.1700
Data Index: 4356330 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.6878. Min Act: -0.1700
Data Index: 4509277 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.6566. Min Act: -0.1700
Data Index: 4838900 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.6253. Min Act: -0.1700
Data Index: 4855722 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.6253. Min Act: -0.1700
Data Index: 6116185 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.5941. Min Act: -0.1700
Data Index: 4732142 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.5941. Min Act: -0.1700
Data Index: 997959 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.5941. Min Act: -0.1700
Data Index: 6161268 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.5941. Min Act: -0.1700
Data Index: 5102969 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4066. Min Range: -6.4066
Max Act: 5.5628. Min Act: -0.1700
Data Index: 6275730 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19