Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.1901. Min Range: -14.1901
Max Act: 14.1901. Min Act: -0.1700
Data Index: 1168700 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.1901. Min Range: -14.1901
Max Act: 13.6276. Min Act: -0.1700
Data Index: 3807491 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.1901. Min Range: -14.1901
Max Act: 13.4401. Min Act: -0.1700
Data Index: 4815150 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.1901. Min Range: -14.1901
Max Act: 13.3151. Min Act: -0.1700
Data Index: 7606821 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.1901. Min Range: -14.1901
Max Act: 13.3151. Min Act: -0.1700
Data Index: 3439204 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.1901. Min Range: -14.1901
Max Act: 13.1276. Min Act: -0.1700
Data Index: 3700221 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.1901. Min Range: -14.1901
Max Act: 13.2526. Min Act: -0.1700
Data Index: 875208 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.8776. Min Act: -0.1700
Data Index: 5362540 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.6276. Min Act: -0.1700
Data Index: 163847 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.6901. Min Act: -0.1700
Data Index: 4260706 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.5651. Min Act: -0.1700
Data Index: 7211413 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.5026. Min Act: -0.1700
Data Index: 5439412 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.5651. Min Act: -0.1700
Data Index: 2870063 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.5026. Min Act: -0.1700
Data Index: 7879811 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.4401. Min Act: -0.1700
Data Index: 7297638 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.3776. Min Act: -0.1700
Data Index: 7598728 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.4401. Min Act: -0.1700
Data Index: 7982925 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.4401. Min Act: -0.1700
Data Index: 1831344 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.3776. Min Act: -0.1700
Data Index: 5984895 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.1901. Min Range: -14.1901
Max Act: 12.3776. Min Act: -0.1700
Data Index: 4552751 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19