Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5924. Min Range: -7.5924
Max Act: 7.5924. Min Act: -0.1700
Data Index: 2277679 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5924. Min Range: -7.5924
Max Act: 7.5924. Min Act: -0.1700
Data Index: 3614920 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5924. Min Range: -7.5924
Max Act: 7.0924. Min Act: -0.1700
Data Index: 6936101 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.8736. Min Act: -0.1700
Data Index: 6936104 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.8424. Min Act: -0.1700
Data Index: 8186955 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.8111. Min Act: -0.1700
Data Index: 2015902 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.8111. Min Act: -0.1700
Data Index: 2979821 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.6861. Min Act: -0.1700
Data Index: 77997 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.6549. Min Act: -0.1700
Data Index: 249293 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.6549. Min Act: -0.1700
Data Index: 27261 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.5924. Min Act: -0.1700
Data Index: 1140973 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.5924. Min Act: -0.1700
Data Index: 1053248 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.5299. Min Act: -0.1700
Data Index: 4125099 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.5611. Min Act: -0.1700
Data Index: 8485676 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.5299. Min Act: -0.1700
Data Index: 5538202 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.5299. Min Act: -0.1700
Data Index: 4763014 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.5299. Min Act: -0.1700
Data Index: 8164976 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.5299. Min Act: -0.1700
Data Index: 4813134 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.5299. Min Act: -0.1700
Data Index: 7380880 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5924. Min Range: -7.5924
Max Act: 6.5299. Min Act: -0.1700
Data Index: 6352729 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19