Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5635. Min Range: -9.5635
Max Act: 9.5635. Min Act: -0.1700
Data Index: 4471926 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5635. Min Range: -9.5635
Max Act: 9.1885. Min Act: -0.1700
Data Index: 4449844 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5635. Min Range: -9.5635
Max Act: 9.0010. Min Act: -0.1700
Data Index: 7973065 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5635. Min Range: -9.5635
Max Act: 9.0635. Min Act: -0.1700
Data Index: 1816947 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5635. Min Range: -9.5635
Max Act: 9.0010. Min Act: -0.1700
Data Index: 8232825 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5635. Min Range: -9.5635
Max Act: 9.0010. Min Act: -0.1700
Data Index: 4143431 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5635. Min Range: -9.5635
Max Act: 9.0010. Min Act: -0.1700
Data Index: 7979973 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.9385. Min Act: -0.1700
Data Index: 5526299 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.9385. Min Act: -0.1700
Data Index: 6758140 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.9385. Min Act: -0.1700
Data Index: 8547517 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.9385. Min Act: -0.1700
Data Index: 1037265 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.8760. Min Act: -0.1700
Data Index: 2385697 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.8135. Min Act: -0.1700
Data Index: 4833425 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.7510. Min Act: -0.1700
Data Index: 7811891 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.7510. Min Act: -0.1700
Data Index: 4767871 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.6885. Min Act: -0.1700
Data Index: 6847608 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.6260. Min Act: -0.1700
Data Index: 8042480 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.6260. Min Act: -0.1700
Data Index: 6407169 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.6260. Min Act: -0.1700
Data Index: 2497213 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5635. Min Range: -9.5635
Max Act: 8.6260. Min Act: -0.1700
Data Index: 3022953 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19