Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1822 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.8250. Min Act: -0.1700
Data Index: 3949793 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.7931. Min Act: -0.1700
Data Index: 2205139 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.7453. Min Act: -0.1700
Data Index: 1925002 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.7293. Min Act: -0.1700
Data Index: 1115307 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.7453. Min Act: -0.1700
Data Index: 496466 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.7293. Min Act: -0.1700
Data Index: 1115308 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.7293. Min Act: -0.1700
Data Index: 6393821 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.7133. Min Act: -0.1700
Data Index: 1734907 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.6813. Min Act: -0.1700
Data Index: 1010838 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.6973. Min Act: -0.1700
Data Index: 1228644 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.6973. Min Act: -0.1700
Data Index: 3949787 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.7133. Min Act: -0.1700
Data Index: 8053400 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.6973. Min Act: -0.1700
Data Index: 4468510 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.6813. Min Act: -0.1700
Data Index: 8128457 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.6653. Min Act: -0.1700
Data Index: 3949782 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.6813. Min Act: -0.1700
Data Index: 8477407 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.6813. Min Act: -0.1700
Data Index: 3162479 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.6813. Min Act: -0.1700
Data Index: 1337643 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.6653. Min Act: -0.1700
Data Index: 3949791 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8250. Min Range: -2.8250
Max Act: 2.6813. Min Act: -0.1700
Data Index: 3949795 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19