Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1090. Min Range: -8.1090
Max Act: 8.1090. Min Act: -0.1700
Data Index: 6602559 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.9215. Min Act: -0.1700
Data Index: 2716967 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.8590. Min Act: -0.1700
Data Index: 8034313 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.7340. Min Act: -0.1700
Data Index: 7918527 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.6715. Min Act: -0.1700
Data Index: 136607 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.6090. Min Act: -0.1700
Data Index: 4292169 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.6090. Min Act: -0.1700
Data Index: 6203878 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.6715. Min Act: -0.1700
Data Index: 680575 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.6090. Min Act: -0.1700
Data Index: 7174390 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.6090. Min Act: -0.1700
Data Index: 5629239 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.5465. Min Act: -0.1700
Data Index: 6602563 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.5465. Min Act: -0.1700
Data Index: 336150 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.5465. Min Act: -0.1700
Data Index: 3463443 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.6090. Min Act: -0.1700
Data Index: 7989834 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.5465. Min Act: -0.1700
Data Index: 5293885 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.5465. Min Act: -0.1700
Data Index: 257851 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.6090. Min Act: -0.1700
Data Index: 4770285 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.5465. Min Act: -0.1700
Data Index: 7734106 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.5465. Min Act: -0.1700
Data Index: 336145 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1090. Min Range: -8.1090
Max Act: 7.4840. Min Act: -0.1700
Data Index: 1247714 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19