Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1738 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1562
Data Index: 6388761 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1700
Data Index: 7211612 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1700
Data Index: 3093667 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1699
Data Index: 7189350 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1700
Data Index: 5698279 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1689
Data Index: 7151408 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1700
Data Index: 2692802 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1700
Data Index: 6954051 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1700
Data Index: 3862568 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1700
Data Index: 6564485 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1697
Data Index: 3333572 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1700
Data Index: 1026576 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1699
Data Index: 601326 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1699
Data Index: 1536315 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1699
Data Index: 6133878 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1677
Data Index: 1196332 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1686
Data Index: 3549929 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1698
Data Index: 3487607 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1695
Data Index: 5996244 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6373. Min Range: -0.6373
Max Act: 0.6373. Min Act: -0.1659
Data Index: 2162683 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19