Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4789 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1056. Min Range: -9.1056
Max Act: 9.1056. Min Act: -0.1700
Data Index: 4399587 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.8556. Min Act: -0.1700
Data Index: 1206633 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.6681. Min Act: -0.1700
Data Index: 5710209 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.5431. Min Act: -0.1700
Data Index: 2371700 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.4181. Min Act: -0.1700
Data Index: 35859 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.4806. Min Act: -0.1700
Data Index: 69121 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.4181. Min Act: -0.1700
Data Index: 1841992 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.3556. Min Act: -0.1700
Data Index: 554820 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.3556. Min Act: -0.1700
Data Index: 554838 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.3556. Min Act: -0.1700
Data Index: 2020356 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.2931. Min Act: -0.1700
Data Index: 8347880 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.2931. Min Act: -0.1700
Data Index: 1206639 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.2931. Min Act: -0.1700
Data Index: 2729118 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.2306. Min Act: -0.1700
Data Index: 2733530 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.2306. Min Act: -0.1700
Data Index: 4772103 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.2306. Min Act: -0.1700
Data Index: 7382067 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.2306. Min Act: -0.1700
Data Index: 7098044 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.1681. Min Act: -0.1700
Data Index: 628697 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.1056. Min Act: -0.1700
Data Index: 3346903 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1056. Min Range: -9.1056
Max Act: 8.1056. Min Act: -0.1700
Data Index: 2399219 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19