Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4878 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.8926. Min Act: -0.1700
Data Index: 8156778 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.8613. Min Act: -0.1700
Data Index: 2581750 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.8301. Min Act: -0.1700
Data Index: 7259733 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.8301. Min Act: -0.1700
Data Index: 5991017 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7988. Min Act: -0.1700
Data Index: 5584954 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.8301. Min Act: -0.1700
Data Index: 5537726 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.8301. Min Act: -0.1700
Data Index: 162830 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7988. Min Act: -0.1700
Data Index: 7185021 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7988. Min Act: -0.1700
Data Index: 32965 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7988. Min Act: -0.1700
Data Index: 6096173 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7988. Min Act: -0.1700
Data Index: 3307806 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7676. Min Act: -0.1700
Data Index: 5342256 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7676. Min Act: -0.1700
Data Index: 2403104 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7363. Min Act: -0.1700
Data Index: 1778633 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7363. Min Act: -0.1700
Data Index: 1531121 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7363. Min Act: -0.1700
Data Index: 1209234 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.6738. Min Act: -0.1700
Data Index: 2851557 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7051. Min Act: -0.1700
Data Index: 3218563 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7051. Min Act: -0.1700
Data Index: 3674559 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8926. Min Range: -4.8926
Max Act: 4.7051. Min Act: -0.1700
Data Index: 5028485 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19