Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2385 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.5115. Min Act: -0.1700
Data Index: 8439288 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.4490. Min Act: -0.1700
Data Index: 7294401 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.3240. Min Act: -0.1700
Data Index: 446912 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.2927. Min Act: -0.1700
Data Index: 7342655 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.2927. Min Act: -0.1700
Data Index: 5141865 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.2302. Min Act: -0.1700
Data Index: 5794550 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.1990. Min Act: -0.1700
Data Index: 3051650 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.1677. Min Act: -0.1700
Data Index: 778672 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.1677. Min Act: -0.1700
Data Index: 470903 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.1052. Min Act: -0.1700
Data Index: 3886973 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.0740. Min Act: -0.1700
Data Index: 1057773 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.0427. Min Act: -0.1700
Data Index: 37487 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.0115. Min Act: -0.1700
Data Index: 1106600 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.0427. Min Act: -0.1700
Data Index: 6923898 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.0115. Min Act: -0.1700
Data Index: 7870893 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5115. Min Range: -6.5115
Max Act: 6.0115. Min Act: -0.1700
Data Index: 7801626 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.9802. Min Act: -0.1700
Data Index: 6433544 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.9490. Min Act: -0.1700
Data Index: 6533622 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.9802. Min Act: -0.1700
Data Index: 8064445 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5115. Min Range: -6.5115
Max Act: 5.9802. Min Act: -0.1700
Data Index: 4162292 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19