Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.9109. Min Act: -0.1700
Data Index: 8177133 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.8484. Min Act: -0.1700
Data Index: 2366751 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.8172. Min Act: -0.1700
Data Index: 6360760 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.7859. Min Act: -0.1700
Data Index: 7793697 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.7859. Min Act: -0.1700
Data Index: 5353904 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.6922. Min Act: -0.1700
Data Index: 3244418 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.5984. Min Act: -0.1700
Data Index: 7743809 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.5984. Min Act: -0.1700
Data Index: 2931862 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.6297. Min Act: -0.1700
Data Index: 6141734 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.5672. Min Act: -0.1700
Data Index: 7073955 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.5359. Min Act: -0.1700
Data Index: 4818732 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.5359. Min Act: -0.1700
Data Index: 4590824 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.5047. Min Act: -0.1700
Data Index: 314439 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.5359. Min Act: -0.1700
Data Index: 8317144 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.5047. Min Act: -0.1700
Data Index: 3380626 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.5047. Min Act: -0.1700
Data Index: 3996816 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.5047. Min Act: -0.1700
Data Index: 7516350 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.4109. Min Act: -0.1700
Data Index: 6898963 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.4422. Min Act: -0.1700
Data Index: 2294535 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9109. Min Range: -5.9109
Max Act: 5.4109. Min Act: -0.1700
Data Index: 1921326 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19