Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3830 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.0805. Min Range: -15.0805
Max Act: 15.0805. Min Act: -0.1700
Data Index: 2208430 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.7055. Min Act: -0.1700
Data Index: 2344475 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.4555. Min Act: -0.1700
Data Index: 7898365 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.3930. Min Act: -0.1700
Data Index: 6673802 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.2680. Min Act: -0.1700
Data Index: 2264220 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.2055. Min Act: -0.1700
Data Index: 217726 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.2055. Min Act: -0.1700
Data Index: 4001984 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.2055. Min Act: -0.1700
Data Index: 8004058 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.2055. Min Act: -0.1700
Data Index: 68144 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.2055. Min Act: -0.1700
Data Index: 6513817 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.1430. Min Act: -0.1700
Data Index: 7655388 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.0805. Min Act: -0.1700
Data Index: 3554850 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.0805. Min Act: -0.1700
Data Index: 6146734 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.0180. Min Act: -0.1700
Data Index: 6418275 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.0805. Min Range: -15.0805
Max Act: 14.0180. Min Act: -0.1700
Data Index: 396624 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.0805. Min Range: -15.0805
Max Act: 13.9555. Min Act: -0.1700
Data Index: 6339470 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.0805. Min Range: -15.0805
Max Act: 13.9555. Min Act: -0.1700
Data Index: 5634921 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.0805. Min Range: -15.0805
Max Act: 13.8930. Min Act: -0.1700
Data Index: 3511470 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.0805. Min Range: -15.0805
Max Act: 13.8930. Min Act: -0.1700
Data Index: 1338672 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.0805. Min Range: -15.0805
Max Act: 13.8930. Min Act: -0.1700
Data Index: 6825364 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19