Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 167 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.8602. Min Act: -0.1700
Data Index: 5787531 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.7664. Min Act: -0.1700
Data Index: 6445672 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.7352. Min Act: -0.1700
Data Index: 6989657 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.6414. Min Act: -0.1700
Data Index: 5043537 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.6102. Min Act: -0.1700
Data Index: 6011340 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.6102. Min Act: -0.1700
Data Index: 2618475 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.6102. Min Act: -0.1700
Data Index: 6445673 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.6102. Min Act: -0.1700
Data Index: 7967126 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.6102. Min Act: -0.1700
Data Index: 8710085 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.5477. Min Act: -0.1700
Data Index: 8506804 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.5164. Min Act: -0.1700
Data Index: 2013162 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4852. Min Act: -0.1700
Data Index: 4246645 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4852. Min Act: -0.1700
Data Index: 4606566 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4852. Min Act: -0.1700
Data Index: 1934196 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4852. Min Act: -0.1700
Data Index: 7120840 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4539. Min Act: -0.1700
Data Index: 1016420 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4539. Min Act: -0.1700
Data Index: 245037 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4539. Min Act: -0.1700
Data Index: 6314372 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4539. Min Act: -0.1700
Data Index: 4781242 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8602. Min Range: -6.8602
Max Act: 6.4539. Min Act: -0.1700
Data Index: 1798752 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19