Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5479 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2344. Min Range: -6.2344
Max Act: 6.2344. Min Act: -0.1700
Data Index: 2742893 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2344. Min Range: -6.2344
Max Act: 6.1406. Min Act: -0.1700
Data Index: 1569595 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.8906. Min Act: -0.1700
Data Index: 1241888 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.8281. Min Act: -0.1700
Data Index: 8174993 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.8594. Min Act: -0.1700
Data Index: 2742894 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.8281. Min Act: -0.1700
Data Index: 919828 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7969. Min Act: -0.1700
Data Index: 1770924 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7969. Min Act: -0.1700
Data Index: 4400709 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7969. Min Act: -0.1700
Data Index: 8127056 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7969. Min Act: -0.1700
Data Index: 1248780 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7969. Min Act: -0.1700
Data Index: 6714760 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.8281. Min Act: -0.1700
Data Index: 7687611 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7969. Min Act: -0.1700
Data Index: 3996044 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7656. Min Act: -0.1700
Data Index: 322519 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7344. Min Act: -0.1700
Data Index: 1661836 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7031. Min Act: -0.1700
Data Index: 6257071 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7344. Min Act: -0.1700
Data Index: 5499545 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7344. Min Act: -0.1700
Data Index: 4781966 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7344. Min Act: -0.1700
Data Index: 7920851 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2344. Min Range: -6.2344
Max Act: 5.7031. Min Act: -0.1700
Data Index: 1382667 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19