Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0798. Min Range: -4.0798
Max Act: 4.0798. Min Act: -0.1700
Data Index: 1888842 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0798. Min Range: -4.0798
Max Act: 4.0798. Min Act: -0.1700
Data Index: 7077752 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0798. Min Range: -4.0798
Max Act: 4.0485. Min Act: -0.1700
Data Index: 6702014 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0798. Min Range: -4.0798
Max Act: 4.0485. Min Act: -0.1700
Data Index: 7071178 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.9548. Min Act: -0.1700
Data Index: 2289947 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.9548. Min Act: -0.1700
Data Index: 6517978 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.9235. Min Act: -0.1700
Data Index: 3187866 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.9548. Min Act: -0.1700
Data Index: 7999468 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.9235. Min Act: -0.1700
Data Index: 8185835 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.9235. Min Act: -0.1700
Data Index: 8413828 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.8922. Min Act: -0.1700
Data Index: 6369659 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.8922. Min Act: -0.1700
Data Index: 5806193 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.8922. Min Act: -0.1700
Data Index: 868634 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.8922. Min Act: -0.1700
Data Index: 5767763 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.8610. Min Act: -0.1700
Data Index: 3059846 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.8610. Min Act: -0.1700
Data Index: 4527415 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.8297. Min Act: -0.1700
Data Index: 3327359 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.8297. Min Act: -0.1700
Data Index: 6060700 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.8610. Min Act: -0.1700
Data Index: 2050960 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0798. Min Range: -4.0798
Max Act: 3.8297. Min Act: -0.1700
Data Index: 5421404 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19