Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.7760. Min Act: -0.1700
Data Index: 632069 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.7291. Min Act: -0.1700
Data Index: 7774376 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6978. Min Act: -0.1700
Data Index: 5060964 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6978. Min Act: -0.1700
Data Index: 4554695 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6509. Min Act: -0.1700
Data Index: 2012658 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6352. Min Act: -0.1700
Data Index: 2518130 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.6352. Min Act: -0.1700
Data Index: 4313991 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.5413. Min Act: -0.1700
Data Index: 2640433 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.5570. Min Act: -0.1700
Data Index: 768531 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.5256. Min Act: -0.1700
Data Index: 1758727 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.5413. Min Act: -0.1700
Data Index: 2267676 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.5100. Min Act: -0.1700
Data Index: 693580 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.5256. Min Act: -0.1700
Data Index: 5900568 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.5256. Min Act: -0.1700
Data Index: 8263991 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.5100. Min Act: -0.1700
Data Index: 7487509 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.5100. Min Act: -0.1700
Data Index: 6907802 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.4943. Min Act: -0.1700
Data Index: 299926 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.4943. Min Act: -0.1700
Data Index: 6888440 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.4943. Min Act: -0.1700
Data Index: 1645696 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7760. Min Range: -3.7760
Max Act: 3.4786. Min Act: -0.1700
Data Index: 963394 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19