Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2410 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2045. Min Range: -4.2045
Max Act: 4.2045. Min Act: -0.1700
Data Index: 4316495 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2045. Min Range: -4.2045
Max Act: 4.2045. Min Act: -0.1700
Data Index: 4448427 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2045. Min Range: -4.2045
Max Act: 4.1732. Min Act: -0.1700
Data Index: 1562759 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2045. Min Range: -4.2045
Max Act: 4.0482. Min Act: -0.1700
Data Index: 3845945 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2045. Min Range: -4.2045
Max Act: 4.0482. Min Act: -0.1700
Data Index: 7026356 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2045. Min Range: -4.2045
Max Act: 4.0169. Min Act: -0.1700
Data Index: 3974078 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2045. Min Range: -4.2045
Max Act: 4.0169. Min Act: -0.1700
Data Index: 4978410 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2045. Min Range: -4.2045
Max Act: 4.0169. Min Act: -0.1700
Data Index: 4113814 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.9857. Min Act: -0.1700
Data Index: 1003421 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.9857. Min Act: -0.1700
Data Index: 4446915 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.9544. Min Act: -0.1700
Data Index: 5498321 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.9231. Min Act: -0.1700
Data Index: 8131703 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.9231. Min Act: -0.1700
Data Index: 7401256 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.9231. Min Act: -0.1700
Data Index: 3249505 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.9231. Min Act: -0.1700
Data Index: 3746339 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.8919. Min Act: -0.1700
Data Index: 6543794 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.9231. Min Act: -0.1700
Data Index: 3219974 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.8919. Min Act: -0.1700
Data Index: 114844 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.8606. Min Act: -0.1700
Data Index: 2783686 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2045. Min Range: -4.2045
Max Act: 3.9231. Min Act: -0.1700
Data Index: 5580949 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19