Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1093 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.6928. Min Act: -0.1700
Data Index: 6085685 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.6303. Min Act: -0.1700
Data Index: 4779068 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.6303. Min Act: -0.1700
Data Index: 7783965 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5678. Min Act: -0.1700
Data Index: 5169046 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5678. Min Act: -0.1700
Data Index: 6341332 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4741. Min Act: -0.1700
Data Index: 8545443 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4741. Min Act: -0.1700
Data Index: 1176564 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 7111759 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 5169036 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 8695325 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.3803. Min Act: -0.1700
Data Index: 1682425 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4116. Min Act: -0.1700
Data Index: 3779169 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4116. Min Act: -0.1700
Data Index: 1694504 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4116. Min Act: -0.1700
Data Index: 4541463 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4116. Min Act: -0.1700
Data Index: 3537188 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.3803. Min Act: -0.1700
Data Index: 7407873 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.3803. Min Act: -0.1700
Data Index: 1337793 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.3491. Min Act: -0.1700
Data Index: 7609579 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.3803. Min Act: -0.1700
Data Index: 7704186 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.3803. Min Act: -0.1700
Data Index: 6959091 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19