Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3341 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.4037. Min Act: -0.1700
Data Index: 3755905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3826. Min Act: -0.1700
Data Index: 3576405 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3896. Min Act: -0.1697
Data Index: 1472921 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3896. Min Act: -0.1700
Data Index: 7173909 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3687. Min Act: -0.1700
Data Index: 1547154 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3618. Min Act: -0.1700
Data Index: 1547155 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3618. Min Act: -0.1699
Data Index: 1640376 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3482. Min Act: -0.1700
Data Index: 4425403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3482. Min Act: -0.1700
Data Index: 3091612 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3414. Min Act: -0.1700
Data Index: 885468 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3482. Min Act: -0.1700
Data Index: 1680721 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3482. Min Act: -0.1700
Data Index: 3786267 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3482. Min Act: -0.1700
Data Index: 3385510 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3482. Min Act: -0.1686
Data Index: 797399 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3482. Min Act: -0.1699
Data Index: 4825327 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3482. Min Act: -0.1700
Data Index: 2232072 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3482. Min Act: -0.1700
Data Index: 5316218 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3482. Min Act: -0.1700
Data Index: 2232687 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3347. Min Act: -0.1700
Data Index: 1547153 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4037. Min Range: -0.4037
Max Act: 0.3482. Min Act: -0.1696
Data Index: 2542252 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19