Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.5828. Min Act: -0.1700
Data Index: 2383324 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.5516. Min Act: -0.1700
Data Index: 1791100 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.3953. Min Act: -0.1700
Data Index: 5054265 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.3328. Min Act: -0.1700
Data Index: 3600824 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.3328. Min Act: -0.1700
Data Index: 1333297 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.3328. Min Act: -0.1700
Data Index: 5984290 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.2391. Min Act: -0.1700
Data Index: 5219769 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.2078. Min Act: -0.1700
Data Index: 3600822 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.2391. Min Act: -0.1700
Data Index: 3600816 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.1766. Min Act: -0.1700
Data Index: 1612983 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.1766. Min Act: -0.1700
Data Index: 3600817 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.1141. Min Act: -0.1700
Data Index: 8424888 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.0828. Min Act: -0.1700
Data Index: 1791101 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.0828. Min Act: -0.1700
Data Index: 2706023 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.0828. Min Act: -0.1700
Data Index: 5892759 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.1141. Min Act: -0.1700
Data Index: 3987779 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.0828. Min Act: -0.1700
Data Index: 951685 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.0516. Min Act: -0.1700
Data Index: 3600827 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.0828. Min Act: -0.1700
Data Index: 1463313 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5828. Min Range: -6.5828
Max Act: 6.0516. Min Act: -0.1700
Data Index: 845421 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19