Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4268 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2167. Min Range: -10.2167
Max Act: 10.2167. Min Act: -0.1700
Data Index: 2006071 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.8417. Min Act: -0.1700
Data Index: 411340 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.8417. Min Act: -0.1700
Data Index: 765379 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.7167. Min Act: -0.1700
Data Index: 639596 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.7167. Min Act: -0.1700
Data Index: 1513696 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.7167. Min Act: -0.1700
Data Index: 1451764 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.5917. Min Act: -0.1700
Data Index: 4966708 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.5917. Min Act: -0.1700
Data Index: 1638068 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.5917. Min Act: -0.1700
Data Index: 7363655 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.5292. Min Act: -0.1700
Data Index: 6290405 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.5292. Min Act: -0.1700
Data Index: 347356 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.4667. Min Act: -0.1700
Data Index: 4148494 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.4667. Min Act: -0.1700
Data Index: 3027492 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.4042. Min Act: -0.1700
Data Index: 2169003 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.4667. Min Act: -0.1700
Data Index: 5043229 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.4667. Min Act: -0.1700
Data Index: 1021065 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.4042. Min Act: -0.1700
Data Index: 5889754 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.4042. Min Act: -0.1700
Data Index: 6301936 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.4042. Min Act: -0.1700
Data Index: 5850938 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2167. Min Range: -10.2167
Max Act: 9.4042. Min Act: -0.1700
Data Index: 739369 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19