Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.9798. Min Act: -0.1700
Data Index: 236564 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.8860. Min Act: -0.1700
Data Index: 6818766 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.7298. Min Act: -0.1700
Data Index: 7235794 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.7298. Min Act: -0.1700
Data Index: 6534642 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.6985. Min Act: -0.1700
Data Index: 1884919 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.6985. Min Act: -0.1700
Data Index: 4602272 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.6360. Min Act: -0.1700
Data Index: 1803466 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.6048. Min Act: -0.1700
Data Index: 4886139 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.6360. Min Act: -0.1700
Data Index: 6477094 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.6048. Min Act: -0.1700
Data Index: 2466747 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.5735. Min Act: -0.1700
Data Index: 4528200 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.5735. Min Act: -0.1700
Data Index: 2571688 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.5423. Min Act: -0.1700
Data Index: 685879 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.5735. Min Act: -0.1700
Data Index: 2201254 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.5735. Min Act: -0.1700
Data Index: 8379734 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.5423. Min Act: -0.1700
Data Index: 4556746 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.5423. Min Act: -0.1700
Data Index: 1580396 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.5423. Min Act: -0.1700
Data Index: 6255664 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.5423. Min Act: -0.1700
Data Index: 913154 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9798. Min Range: -7.9798
Max Act: 7.5423. Min Act: -0.1700
Data Index: 7919669 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19