Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1619 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.9209. Min Act: -0.1700
Data Index: 7897786 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.8584. Min Act: -0.1700
Data Index: 2933865 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.7959. Min Act: -0.1700
Data Index: 1113555 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.7647. Min Act: -0.1700
Data Index: 492519 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.7647. Min Act: -0.1700
Data Index: 3344472 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.7334. Min Act: -0.1700
Data Index: 3932864 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.6397. Min Act: -0.1700
Data Index: 8033515 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.5772. Min Act: -0.1700
Data Index: 283905 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.5459. Min Act: -0.1700
Data Index: 5771963 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.5459. Min Act: -0.1700
Data Index: 4575758 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.5459. Min Act: -0.1700
Data Index: 6638610 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.5147. Min Act: -0.1700
Data Index: 6796139 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.5459. Min Act: -0.1700
Data Index: 7164937 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.4834. Min Act: -0.1700
Data Index: 6493474 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.4834. Min Act: -0.1700
Data Index: 6960699 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.4834. Min Act: -0.1700
Data Index: 5298040 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.4522. Min Act: -0.1700
Data Index: 5162006 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.4209. Min Act: -0.1700
Data Index: 3867929 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.4834. Min Act: -0.1700
Data Index: 3201040 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9209. Min Range: -6.9209
Max Act: 6.4522. Min Act: -0.1700
Data Index: 7338840 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19