Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.3949. Min Act: -0.1700
Data Index: 1418444 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.3324. Min Act: -0.1700
Data Index: 4785752 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.3012. Min Act: -0.1700
Data Index: 5929238 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.2699. Min Act: -0.1700
Data Index: 4847710 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.2074. Min Act: -0.1700
Data Index: 8498699 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.2074. Min Act: -0.1700
Data Index: 3638561 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1762. Min Act: -0.1700
Data Index: 3811665 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1762. Min Act: -0.1700
Data Index: 6883815 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1762. Min Act: -0.1700
Data Index: 2046602 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1762. Min Act: -0.1700
Data Index: 5717202 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1762. Min Act: -0.1700
Data Index: 8127296 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1449. Min Act: -0.1700
Data Index: 7706680 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1449. Min Act: -0.1700
Data Index: 1346225 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1449. Min Act: -0.1700
Data Index: 86395 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1449. Min Act: -0.1700
Data Index: 5277400 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1137. Min Act: -0.1700
Data Index: 7934776 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1137. Min Act: -0.1700
Data Index: 2084898 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.1137. Min Act: -0.1700
Data Index: 5032583 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.0824. Min Act: -0.1700
Data Index: 6412664 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3949. Min Range: -6.3949
Max Act: 6.0824. Min Act: -0.1700
Data Index: 2132555 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19