Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5098 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.7084. Min Act: -0.1700
Data Index: 2563225 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.4584. Min Act: -0.1700
Data Index: 8162982 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.3646. Min Act: -0.1700
Data Index: 4654085 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.3646. Min Act: -0.1700
Data Index: 1710661 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.3646. Min Act: -0.1700
Data Index: 4764623 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.3646. Min Act: -0.1700
Data Index: 6556650 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.3334. Min Act: -0.1700
Data Index: 1098491 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.3334. Min Act: -0.1700
Data Index: 476786 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.3334. Min Act: -0.1700
Data Index: 5569657 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.3334. Min Act: -0.1700
Data Index: 1857864 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.3021. Min Act: -0.1700
Data Index: 6163376 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.2709. Min Act: -0.1700
Data Index: 6246012 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.2709. Min Act: -0.1700
Data Index: 5240370 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.3021. Min Act: -0.1700
Data Index: 2156924 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.2709. Min Act: -0.1700
Data Index: 765302 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.2709. Min Act: -0.1700
Data Index: 5165376 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.2396. Min Act: -0.1700
Data Index: 2200996 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.2396. Min Act: -0.1700
Data Index: 460783 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.2396. Min Act: -0.1700
Data Index: 766018 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7084. Min Range: -6.7084
Max Act: 6.2396. Min Act: -0.1700
Data Index: 3357068 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19