Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 955 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.4718. Min Act: -0.1700
Data Index: 1092175 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.2842. Min Act: -0.1700
Data Index: 1594997 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.2842. Min Act: -0.1700
Data Index: 3226850 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.2530. Min Act: -0.1700
Data Index: 7160272 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.2217. Min Act: -0.1700
Data Index: 2795341 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.2217. Min Act: -0.1700
Data Index: 324457 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.1905. Min Act: -0.1700
Data Index: 6651352 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.1905. Min Act: -0.1700
Data Index: 2535715 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.1905. Min Act: -0.1700
Data Index: 4234558 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.2217. Min Act: -0.1700
Data Index: 6687581 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.1592. Min Act: -0.1700
Data Index: 31330 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.1280. Min Act: -0.1700
Data Index: 2648209 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.1592. Min Act: -0.1700
Data Index: 6562664 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.1592. Min Act: -0.1700
Data Index: 3053874 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.1280. Min Act: -0.1700
Data Index: 1638276 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.1592. Min Act: -0.1700
Data Index: 2169705 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.1280. Min Act: -0.1700
Data Index: 1533631 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.0967. Min Act: -0.1700
Data Index: 2244474 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.0967. Min Act: -0.1700
Data Index: 6577280 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4718. Min Range: -4.4718
Max Act: 4.1280. Min Act: -0.1700
Data Index: 2869587 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19