Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2415 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.6929. Min Act: -0.1700
Data Index: 7927188 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.5991. Min Act: -0.1700
Data Index: 5043779 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.5366. Min Act: -0.1700
Data Index: 4617957 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.5366. Min Act: -0.1700
Data Index: 1880610 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.5054. Min Act: -0.1700
Data Index: 6445894 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.5054. Min Act: -0.1700
Data Index: 8455682 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.5054. Min Act: -0.1700
Data Index: 5564650 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.4741. Min Act: -0.1700
Data Index: 7802224 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.4741. Min Act: -0.1700
Data Index: 2073793 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.4429. Min Act: -0.1700
Data Index: 2782875 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.4429. Min Act: -0.1700
Data Index: 3091910 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.4429. Min Act: -0.1700
Data Index: 6191007 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.4429. Min Act: -0.1700
Data Index: 110841 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.4116. Min Act: -0.1700
Data Index: 567480 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.4116. Min Act: -0.1700
Data Index: 8813354 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.3491. Min Act: -0.1700
Data Index: 3399412 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.3491. Min Act: -0.1700
Data Index: 6575892 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.3804. Min Act: -0.1700
Data Index: 2181063 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.3804. Min Act: -0.1700
Data Index: 1376071 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6929. Min Range: -5.6929
Max Act: 5.3491. Min Act: -0.1700
Data Index: 3016834 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19