Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4603 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5821. Min Range: -7.5821
Max Act: 7.5821. Min Act: -0.1700
Data Index: 4311766 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5821. Min Range: -7.5821
Max Act: 7.3946. Min Act: -0.1700
Data Index: 5227734 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5821. Min Range: -7.5821
Max Act: 7.0821. Min Act: -0.1700
Data Index: 8674039 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.8321. Min Act: -0.1700
Data Index: 8118370 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.8634. Min Act: -0.1700
Data Index: 3468061 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.8321. Min Act: -0.1700
Data Index: 2555096 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.8321. Min Act: -0.1700
Data Index: 4065340 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.8009. Min Act: -0.1700
Data Index: 7945048 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.7696. Min Act: -0.1700
Data Index: 5668929 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.7384. Min Act: -0.1700
Data Index: 5790534 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.7384. Min Act: -0.1700
Data Index: 3372944 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.7384. Min Act: -0.1700
Data Index: 1336645 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.7384. Min Act: -0.1700
Data Index: 6741988 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.7384. Min Act: -0.1700
Data Index: 6574589 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.7071. Min Act: -0.1700
Data Index: 5156982 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.7071. Min Act: -0.1700
Data Index: 3851108 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.6759. Min Act: -0.1700
Data Index: 1594578 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.6759. Min Act: -0.1700
Data Index: 6543672 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.6134. Min Act: -0.1700
Data Index: 7813325 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5821. Min Range: -7.5821
Max Act: 6.6446. Min Act: -0.1700
Data Index: 5788971 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19