Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4407 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1977. Min Range: -8.1977
Max Act: 8.1977. Min Act: -0.1700
Data Index: 8285100 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1977. Min Range: -8.1977
Max Act: 8.0415. Min Act: -0.1700
Data Index: 2818491 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.9165. Min Act: -0.1700
Data Index: 4249919 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.6977. Min Act: -0.1700
Data Index: 913815 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.6665. Min Act: -0.1700
Data Index: 8223551 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.6352. Min Act: -0.1700
Data Index: 3871176 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.5415. Min Act: -0.1700
Data Index: 3541406 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.5415. Min Act: -0.1700
Data Index: 5755113 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.5727. Min Act: -0.1700
Data Index: 8302832 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.5415. Min Act: -0.1700
Data Index: 2530967 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.4790. Min Act: -0.1700
Data Index: 7481453 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.5102. Min Act: -0.1700
Data Index: 869162 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.5102. Min Act: -0.1700
Data Index: 6312183 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.5102. Min Act: -0.1700
Data Index: 6859276 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.5415. Min Act: -0.1700
Data Index: 1307862 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.4790. Min Act: -0.1700
Data Index: 8343566 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.4165. Min Act: -0.1700
Data Index: 6458862 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.3852. Min Act: -0.1700
Data Index: 7401044 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.4165. Min Act: -0.1700
Data Index: 7221263 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1977. Min Range: -8.1977
Max Act: 7.4165. Min Act: -0.1700
Data Index: 5017044 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19