Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3680 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.8826. Min Act: -0.1699
Data Index: 623941 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.8191. Min Act: -0.1695
Data Index: 1258694 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.8031. Min Act: -0.1699
Data Index: 3107872 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.8031. Min Act: -0.1696
Data Index: 104244 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.8031. Min Act: -0.1700
Data Index: 6236134 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.8031. Min Act: -0.1699
Data Index: 5104046 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7872. Min Act: -0.1700
Data Index: 1746405 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7872. Min Act: -0.1699
Data Index: 5860009 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.8031. Min Act: -0.1700
Data Index: 6246970 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7872. Min Act: -0.1700
Data Index: 6358833 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7713. Min Act: -0.1700
Data Index: 3545532 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7713. Min Act: -0.1700
Data Index: 5339429 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7553. Min Act: -0.1700
Data Index: 6567528 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7713. Min Act: -0.1700
Data Index: 4322841 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7713. Min Act: -0.1699
Data Index: 4142828 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7713. Min Act: -0.1700
Data Index: 5157580 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7553. Min Act: -0.1700
Data Index: 6311929 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7553. Min Act: -0.1700
Data Index: 1972870 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7553. Min Act: -0.1698
Data Index: 8243183 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8826. Min Range: -2.8826
Max Act: 2.7553. Min Act: -0.1700
Data Index: 4511679 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19