Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4899 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.7821. Min Act: -0.1700
Data Index: 5330159 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.5634. Min Act: -0.1700
Data Index: 6495659 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.5009. Min Act: -0.1700
Data Index: 6247449 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.2821. Min Act: -0.1700
Data Index: 7508961 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.2196. Min Act: -0.1700
Data Index: 1952170 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.1571. Min Act: -0.1700
Data Index: 5046876 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.1571. Min Act: -0.1700
Data Index: 45863 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.1571. Min Act: -0.1700
Data Index: 1322041 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.1571. Min Act: -0.1700
Data Index: 36806 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.1259. Min Act: -0.1700
Data Index: 2720341 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.0634. Min Act: -0.1700
Data Index: 887185 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.0634. Min Act: -0.1700
Data Index: 7749440 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.0634. Min Act: -0.1700
Data Index: 713970 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.0321. Min Act: -0.1700
Data Index: 5111953 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.0321. Min Act: -0.1700
Data Index: 6508856 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7821. Min Range: -6.7821
Max Act: 5.9696. Min Act: -0.1700
Data Index: 858071 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.0009. Min Act: -0.1700
Data Index: 5426522 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.0009. Min Act: -0.1700
Data Index: 7554620 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7821. Min Range: -6.7821
Max Act: 6.0009. Min Act: -0.1700
Data Index: 5817847 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7821. Min Range: -6.7821
Max Act: 5.9696. Min Act: -0.1700
Data Index: 2696802 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19