Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.2419. Min Act: -0.1700
Data Index: 5370785 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.2419. Min Act: -0.1700
Data Index: 7989392 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.2419. Min Act: -0.1700
Data Index: 7012997 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.1794. Min Act: -0.1700
Data Index: 4854242 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.1169. Min Act: -0.1700
Data Index: 8254737 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.0544. Min Act: -0.1700
Data Index: 5568791 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.1169. Min Act: -0.1700
Data Index: 379508 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.1169. Min Act: -0.1700
Data Index: 6841721 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.0544. Min Act: -0.1700
Data Index: 1632482 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.0544. Min Act: -0.1700
Data Index: 4564711 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.0544. Min Act: -0.1700
Data Index: 5431992 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.0544. Min Act: -0.1700
Data Index: 8216754 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2419. Min Range: -9.2419
Max Act: 9.0544. Min Act: -0.1700
Data Index: 2233849 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2419. Min Range: -9.2419
Max Act: 8.9919. Min Act: -0.1700
Data Index: 3245062 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2419. Min Range: -9.2419
Max Act: 8.9919. Min Act: -0.1700
Data Index: 4607959 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2419. Min Range: -9.2419
Max Act: 8.9294. Min Act: -0.1700
Data Index: 1741756 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2419. Min Range: -9.2419
Max Act: 8.8669. Min Act: -0.1700
Data Index: 2915991 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2419. Min Range: -9.2419
Max Act: 8.8669. Min Act: -0.1700
Data Index: 4209651 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2419. Min Range: -9.2419
Max Act: 8.8669. Min Act: -0.1700
Data Index: 8049473 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2419. Min Range: -9.2419
Max Act: 8.8669. Min Act: -0.1700
Data Index: 8442652 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19