Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 6 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.9609. Min Act: -0.1700
Data Index: 8280823 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.9099. Min Act: -0.1693
Data Index: 5088006 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8244. Min Act: -0.1699
Data Index: 4702645 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8244. Min Act: -0.1700
Data Index: 4908375 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.8244. Min Act: -0.1697
Data Index: 5088007 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7900. Min Act: -0.1700
Data Index: 2171492 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7728. Min Act: -0.1700
Data Index: 2133898 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7555. Min Act: -0.1699
Data Index: 478354 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7555. Min Act: -0.1700
Data Index: 856855 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7555. Min Act: -0.1695
Data Index: 2651637 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7209. Min Act: -0.1700
Data Index: 1807915 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7036. Min Act: -0.1700
Data Index: 1892715 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7382. Min Act: -0.1700
Data Index: 1774862 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7209. Min Act: -0.1700
Data Index: 8418142 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7036. Min Act: -0.1692
Data Index: 1438890 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7036. Min Act: -0.1697
Data Index: 1185971 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7036. Min Act: -0.1700
Data Index: 8117523 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.6863. Min Act: -0.1689
Data Index: 5726042 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.6863. Min Act: -0.1687
Data Index: 2243894 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9609. Min Range: -1.9609
Max Act: 1.7209. Min Act: -0.1700
Data Index: 6253093 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19