Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1584. Min Range: -7.1584
Max Act: 7.1584. Min Act: -0.1700
Data Index: 1288709 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.8459. Min Act: -0.1700
Data Index: 5256463 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.8459. Min Act: -0.1700
Data Index: 3009513 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.7834. Min Act: -0.1700
Data Index: 3834340 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.7209. Min Act: -0.1700
Data Index: 4689765 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.7209. Min Act: -0.1700
Data Index: 8459852 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.7209. Min Act: -0.1700
Data Index: 7891792 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.7209. Min Act: -0.1700
Data Index: 5130317 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.6271. Min Act: -0.1700
Data Index: 2924225 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.6271. Min Act: -0.1700
Data Index: 8148653 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.6584. Min Act: -0.1700
Data Index: 4540863 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.6271. Min Act: -0.1700
Data Index: 1456607 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.5959. Min Act: -0.1700
Data Index: 3954680 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.5959. Min Act: -0.1700
Data Index: 7425100 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.5646. Min Act: -0.1700
Data Index: 1636133 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.5334. Min Act: -0.1700
Data Index: 3268147 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.5334. Min Act: -0.1700
Data Index: 4516899 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.5334. Min Act: -0.1700
Data Index: 6800815 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.5021. Min Act: -0.1700
Data Index: 5471786 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1584. Min Range: -7.1584
Max Act: 6.5021. Min Act: -0.1700
Data Index: 2122990 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19