Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 880 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2798. Min Range: -6.2798
Max Act: 6.2798. Min Act: -0.1700
Data Index: 5465143 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2798. Min Range: -6.2798
Max Act: 6.0923. Min Act: -0.1700
Data Index: 7463013 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.9673. Min Act: -0.1700
Data Index: 4619088 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.9673. Min Act: -0.1700
Data Index: 5473852 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.9673. Min Act: -0.1700
Data Index: 8813617 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.9360. Min Act: -0.1700
Data Index: 6814134 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.9360. Min Act: -0.1700
Data Index: 7915853 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.9360. Min Act: -0.1700
Data Index: 2137444 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.9048. Min Act: -0.1700
Data Index: 4246659 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.9048. Min Act: -0.1700
Data Index: 6137784 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.8735. Min Act: -0.1700
Data Index: 585343 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.8423. Min Act: -0.1700
Data Index: 6799370 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.8423. Min Act: -0.1700
Data Index: 2282779 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.8423. Min Act: -0.1700
Data Index: 8728897 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.8110. Min Act: -0.1700
Data Index: 7510910 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.8110. Min Act: -0.1700
Data Index: 8013340 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.7485. Min Act: -0.1700
Data Index: 6331230 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.7798. Min Act: -0.1700
Data Index: 4798900 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.7798. Min Act: -0.1700
Data Index: 5555595 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2798. Min Range: -6.2798
Max Act: 5.7485. Min Act: -0.1700
Data Index: 7790479 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19