Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3800 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.8870. Min Act: -0.1700
Data Index: 1586179 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.8558. Min Act: -0.1700
Data Index: 3884361 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.7932. Min Act: -0.1700
Data Index: 5751890 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.7463. Min Act: -0.1700
Data Index: 2245538 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.7619. Min Act: -0.1700
Data Index: 2182927 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.7307. Min Act: -0.1700
Data Index: 1896261 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.7307. Min Act: -0.1700
Data Index: 2244000 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.7150. Min Act: -0.1700
Data Index: 2948527 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.6681. Min Act: -0.1700
Data Index: 455778 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.6681. Min Act: -0.1700
Data Index: 4083751 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.6681. Min Act: -0.1700
Data Index: 7778555 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.6524. Min Act: -0.1700
Data Index: 2414726 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.6368. Min Act: -0.1700
Data Index: 1170784 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.6212. Min Act: -0.1700
Data Index: 3703635 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.6212. Min Act: -0.1700
Data Index: 8410854 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.6212. Min Act: -0.1700
Data Index: 7508735 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.5899. Min Act: -0.1700
Data Index: 7992896 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.6055. Min Act: -0.1700
Data Index: 6084079 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.5899. Min Act: -0.1700
Data Index: 4928651 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8870. Min Range: -3.8870
Max Act: 3.5899. Min Act: -0.1700
Data Index: 5751897 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19