Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1991. Min Range: -5.1991
Max Act: 5.1991. Min Act: -0.1700
Data Index: 4336827 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1991. Min Range: -5.1991
Max Act: 5.0741. Min Act: -0.1700
Data Index: 8498444 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1991. Min Range: -5.1991
Max Act: 5.0428. Min Act: -0.1700
Data Index: 6340783 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.9803. Min Act: -0.1700
Data Index: 429821 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.7928. Min Act: -0.1700
Data Index: 8506204 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.7303. Min Act: -0.1700
Data Index: 3416667 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.7303. Min Act: -0.1700
Data Index: 4732119 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.7303. Min Act: -0.1700
Data Index: 7838759 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.6991. Min Act: -0.1700
Data Index: 3013997 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.6678. Min Act: -0.1700
Data Index: 7280233 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.6366. Min Act: -0.1700
Data Index: 7116784 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.6053. Min Act: -0.1700
Data Index: 6309164 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.6366. Min Act: -0.1700
Data Index: 8490729 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.6366. Min Act: -0.1700
Data Index: 7870936 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.6366. Min Act: -0.1700
Data Index: 6340782 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.6053. Min Act: -0.1700
Data Index: 3286672 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.5741. Min Act: -0.1700
Data Index: 159770 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.5428. Min Act: -0.1700
Data Index: 6536800 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.5741. Min Act: -0.1700
Data Index: 1088132 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1991. Min Range: -5.1991
Max Act: 4.5741. Min Act: -0.1700
Data Index: 4432315 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19