Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0207. Min Range: -10.0207
Max Act: 10.0207. Min Act: -0.1700
Data Index: 3335527 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.6457. Min Act: -0.1700
Data Index: 1510288 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.5832. Min Act: -0.1700
Data Index: 4957770 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.5207. Min Act: -0.1700
Data Index: 6644663 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.5207. Min Act: -0.1700
Data Index: 2766274 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.3957. Min Act: -0.1700
Data Index: 4833078 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.3957. Min Act: -0.1700
Data Index: 6684138 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.3957. Min Act: -0.1700
Data Index: 8232576 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.3332. Min Act: -0.1700
Data Index: 1336136 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.2707. Min Act: -0.1700
Data Index: 7437303 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.2082. Min Act: -0.1700
Data Index: 8599560 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.2082. Min Act: -0.1700
Data Index: 1370611 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.2082. Min Act: -0.1700
Data Index: 7636050 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.1457. Min Act: -0.1700
Data Index: 3262800 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.1457. Min Act: -0.1700
Data Index: 123006 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.1457. Min Act: -0.1700
Data Index: 6664740 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.1457. Min Act: -0.1700
Data Index: 4650234 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.1457. Min Act: -0.1700
Data Index: 5815034 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.0832. Min Act: -0.1700
Data Index: 6361762 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0207. Min Range: -10.0207
Max Act: 9.0832. Min Act: -0.1700
Data Index: 2936748 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19