Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 993 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.9751. Min Act: -0.1700
Data Index: 2928650 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.8813. Min Act: -0.1700
Data Index: 4240557 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.8813. Min Act: -0.1700
Data Index: 6747082 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.8188. Min Act: -0.1700
Data Index: 4633981 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.7876. Min Act: -0.1700
Data Index: 6881045 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.7251. Min Act: -0.1700
Data Index: 4536584 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.6626. Min Act: -0.1700
Data Index: 6407760 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.7251. Min Act: -0.1700
Data Index: 6824327 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.6313. Min Act: -0.1700
Data Index: 5911341 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.6938. Min Act: -0.1700
Data Index: 2308815 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.7251. Min Act: -0.1700
Data Index: 7279559 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.6313. Min Act: -0.1700
Data Index: 4142598 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.6001. Min Act: -0.1700
Data Index: 5372414 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.6001. Min Act: -0.1700
Data Index: 984187 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.5376. Min Act: -0.1700
Data Index: 245826 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.5376. Min Act: -0.1700
Data Index: 340331 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.5063. Min Act: -0.1700
Data Index: 1195719 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.5376. Min Act: -0.1700
Data Index: 314407 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.5063. Min Act: -0.1700
Data Index: 5935420 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9751. Min Range: -5.9751
Max Act: 5.4126. Min Act: -0.1700
Data Index: 579616 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19