Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4303 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.3340. Min Act: -0.1700
Data Index: 575444 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.3027. Min Act: -0.1700
Data Index: 3974148 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.3027. Min Act: -0.1700
Data Index: 5528082 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.2715. Min Act: -0.1700
Data Index: 109650 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.2402. Min Act: -0.1700
Data Index: 5528099 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.1777. Min Act: -0.1700
Data Index: 4141014 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.1465. Min Act: -0.1700
Data Index: 1590435 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.1465. Min Act: -0.1700
Data Index: 3080713 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.1465. Min Act: -0.1700
Data Index: 5930286 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.1465. Min Act: -0.1700
Data Index: 816505 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.1465. Min Act: -0.1700
Data Index: 7826782 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.1465. Min Act: -0.1700
Data Index: 2662669 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.1465. Min Act: -0.1700
Data Index: 3887913 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.1152. Min Act: -0.1700
Data Index: 1657211 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.1152. Min Act: -0.1700
Data Index: 8519679 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.0840. Min Act: -0.1700
Data Index: 5528773 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.0215. Min Act: -0.1700
Data Index: 2306782 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.0215. Min Act: -0.1700
Data Index: 8415322 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.0215. Min Act: -0.1700
Data Index: 8427973 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3340. Min Range: -6.3340
Max Act: 6.0215. Min Act: -0.1700
Data Index: 3365392 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19