Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4320 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.3503. Min Act: -0.1700
Data Index: 7291958 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1941. Min Act: -0.1700
Data Index: 6379896 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1941. Min Act: -0.1700
Data Index: 7242552 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1628. Min Act: -0.1700
Data Index: 7773682 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1941. Min Act: -0.1700
Data Index: 4863414 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1941. Min Act: -0.1700
Data Index: 6460691 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1628. Min Act: -0.1700
Data Index: 5455949 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1941. Min Act: -0.1700
Data Index: 6943826 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1628. Min Act: -0.1700
Data Index: 6514162 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1628. Min Act: -0.1700
Data Index: 352703 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1628. Min Act: -0.1700
Data Index: 7571869 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1315. Min Act: -0.1700
Data Index: 682236 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1315. Min Act: -0.1700
Data Index: 5004582 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1315. Min Act: -0.1700
Data Index: 7753812 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1315. Min Act: -0.1700
Data Index: 6038893 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1003. Min Act: -0.1700
Data Index: 6271791 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1003. Min Act: -0.1700
Data Index: 8184563 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1003. Min Act: -0.1700
Data Index: 7303130 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.1315. Min Act: -0.1700
Data Index: 3754107 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3503. Min Range: -4.3503
Max Act: 4.0378. Min Act: -0.1700
Data Index: 268373 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19