Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.7204. Min Act: -0.1700
Data Index: 1277590 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.5954. Min Act: -0.1700
Data Index: 6972910 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.5017. Min Act: -0.1700
Data Index: 8787393 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.3767. Min Act: -0.1700
Data Index: 5818116 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2829. Min Act: -0.1700
Data Index: 7075094 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2517. Min Act: -0.1700
Data Index: 271871 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2204. Min Act: -0.1700
Data Index: 7853413 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2204. Min Act: -0.1700
Data Index: 5483108 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.1892. Min Act: -0.1700
Data Index: 4881931 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.1579. Min Act: -0.1700
Data Index: 1663506 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.1892. Min Act: -0.1700
Data Index: 2641899 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.1579. Min Act: -0.1700
Data Index: 2084120 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.1579. Min Act: -0.1700
Data Index: 5612586 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.1267. Min Act: -0.1700
Data Index: 7535829 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.1267. Min Act: -0.1700
Data Index: 2523077 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.0954. Min Act: -0.1700
Data Index: 7203718 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.0954. Min Act: -0.1700
Data Index: 5080655 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.0954. Min Act: -0.1700
Data Index: 6300122 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.0642. Min Act: -0.1700
Data Index: 67385 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.0642. Min Act: -0.1700
Data Index: 3163710 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19