Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6336 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.2246. Min Act: -0.1700
Data Index: 529462 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.1933. Min Act: -0.1700
Data Index: 1822037 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.1621. Min Act: -0.1700
Data Index: 7979656 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.1308. Min Act: -0.1700
Data Index: 6676093 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.0996. Min Act: -0.1700
Data Index: 6172694 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.0996. Min Act: -0.1700
Data Index: 1586679 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.0683. Min Act: -0.1700
Data Index: 6469919 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.0371. Min Act: -0.1700
Data Index: 742894 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.0371. Min Act: -0.1700
Data Index: 8643866 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.0371. Min Act: -0.1700
Data Index: 4708049 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.0371. Min Act: -0.1700
Data Index: 6719729 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.0683. Min Act: -0.1700
Data Index: 3026926 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2246. Min Range: -6.2246
Max Act: 6.0058. Min Act: -0.1700
Data Index: 1165061 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2246. Min Range: -6.2246
Max Act: 5.9746. Min Act: -0.1700
Data Index: 3718555 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2246. Min Range: -6.2246
Max Act: 5.9746. Min Act: -0.1700
Data Index: 3720826 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2246. Min Range: -6.2246
Max Act: 5.9746. Min Act: -0.1700
Data Index: 6809546 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2246. Min Range: -6.2246
Max Act: 5.9746. Min Act: -0.1700
Data Index: 7206823 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2246. Min Range: -6.2246
Max Act: 5.9433. Min Act: -0.1700
Data Index: 8504880 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2246. Min Range: -6.2246
Max Act: 5.9746. Min Act: -0.1700
Data Index: 2055190 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2246. Min Range: -6.2246
Max Act: 5.9746. Min Act: -0.1700
Data Index: 2597949 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19