Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4632 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1718. Min Range: -10.1718
Max Act: 10.1718. Min Act: -0.1700
Data Index: 7249436 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.9218. Min Act: -0.1700
Data Index: 3666432 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.7343. Min Act: -0.1700
Data Index: 7835359 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.7343. Min Act: -0.1700
Data Index: 5805383 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.7343. Min Act: -0.1700
Data Index: 2000132 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.5468. Min Act: -0.1700
Data Index: 2116841 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.4843. Min Act: -0.1700
Data Index: 801377 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.2968. Min Act: -0.1700
Data Index: 2227424 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.2968. Min Act: -0.1700
Data Index: 8634594 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.2968. Min Act: -0.1700
Data Index: 1701287 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.2343. Min Act: -0.1700
Data Index: 5949210 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.2343. Min Act: -0.1700
Data Index: 5742146 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.2343. Min Act: -0.1700
Data Index: 3669579 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.2343. Min Act: -0.1700
Data Index: 1725425 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.2343. Min Act: -0.1700
Data Index: 2887242 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.1718. Min Act: -0.1700
Data Index: 3416802 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.1718. Min Act: -0.1700
Data Index: 7093756 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.1718. Min Act: -0.1700
Data Index: 7295935 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.1093. Min Act: -0.1700
Data Index: 3084682 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1718. Min Range: -10.1718
Max Act: 9.0468. Min Act: -0.1700
Data Index: 6074024 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19