Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5959 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.0313. Min Range: -14.0313
Max Act: 14.0313. Min Act: -0.1700
Data Index: 4933453 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.0313. Min Range: -14.0313
Max Act: 13.2188. Min Act: -0.1700
Data Index: 8547767 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.7813. Min Act: -0.1700
Data Index: 5157859 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.6563. Min Act: -0.1700
Data Index: 6246025 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.5938. Min Act: -0.1700
Data Index: 1536001 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.5313. Min Act: -0.1700
Data Index: 3677336 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.5313. Min Act: -0.1700
Data Index: 3017928 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.4063. Min Act: -0.1700
Data Index: 6597397 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.4688. Min Act: -0.1700
Data Index: 7151379 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.4063. Min Act: -0.1700
Data Index: 6350384 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.3438. Min Act: -0.1700
Data Index: 4280970 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.4063. Min Act: -0.1700
Data Index: 1854435 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.3438. Min Act: -0.1700
Data Index: 2305577 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.3438. Min Act: -0.1700
Data Index: 2023847 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.3438. Min Act: -0.1700
Data Index: 3603684 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.3438. Min Act: -0.1700
Data Index: 1750138 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.2813. Min Act: -0.1700
Data Index: 6462779 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.2813. Min Act: -0.1700
Data Index: 4833161 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.2813. Min Act: -0.1700
Data Index: 4505689 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.0313. Min Range: -14.0313
Max Act: 12.2813. Min Act: -0.1700
Data Index: 7265440 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19