Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2353 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.8826. Min Act: -0.1700
Data Index: 1618352 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.6951. Min Act: -0.1700
Data Index: 5019962 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.6951. Min Act: -0.1700
Data Index: 4169213 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.6638. Min Act: -0.1700
Data Index: 6511631 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.6638. Min Act: -0.1700
Data Index: 5303610 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.6326. Min Act: -0.1700
Data Index: 8002794 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.6013. Min Act: -0.1700
Data Index: 1684082 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.6013. Min Act: -0.1700
Data Index: 8249227 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.5701. Min Act: -0.1700
Data Index: 4063879 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.5701. Min Act: -0.1700
Data Index: 1444826 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.5388. Min Act: -0.1700
Data Index: 4307263 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.5388. Min Act: -0.1700
Data Index: 8766425 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.5701. Min Act: -0.1700
Data Index: 3230412 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.5388. Min Act: -0.1700
Data Index: 4840211 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.5076. Min Act: -0.1700
Data Index: 2544502 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.4763. Min Act: -0.1700
Data Index: 1575923 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.4763. Min Act: -0.1700
Data Index: 2872888 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.4451. Min Act: -0.1700
Data Index: 947407 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.4138. Min Act: -0.1700
Data Index: 7512687 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8826. Min Range: -6.8826
Max Act: 6.4451. Min Act: -0.1700
Data Index: 853155 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19