Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 479 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.6408. Min Act: -0.1700
Data Index: 5607498 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.5442. Min Act: -0.1700
Data Index: 626438 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.5442. Min Act: -0.1700
Data Index: 3357968 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.5603. Min Act: -0.1700
Data Index: 8320784 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.5280. Min Act: -0.1700
Data Index: 6771579 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4957. Min Act: -0.1700
Data Index: 6876974 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4957. Min Act: -0.1700
Data Index: 4279502 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.5119. Min Act: -0.1700
Data Index: 1313084 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4957. Min Act: -0.1700
Data Index: 7941486 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.5119. Min Act: -0.1700
Data Index: 2105460 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4794. Min Act: -0.1700
Data Index: 2753876 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4794. Min Act: -0.1700
Data Index: 7333541 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4794. Min Act: -0.1700
Data Index: 8664874 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4470. Min Act: -0.1700
Data Index: 2899425 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4794. Min Act: -0.1700
Data Index: 8303762 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4794. Min Act: -0.1700
Data Index: 3869573 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4794. Min Act: -0.1700
Data Index: 279967 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4632. Min Act: -0.1700
Data Index: 6777414 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4632. Min Act: -0.1700
Data Index: 3303943 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6408. Min Range: -2.6408
Max Act: 2.4632. Min Act: -0.1700
Data Index: 1445067 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19