Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 476 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.9057. Min Act: -0.1700
Data Index: 6615184 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.8588. Min Act: -0.1700
Data Index: 7645784 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.7962. Min Act: -0.1700
Data Index: 8417036 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.7650. Min Act: -0.1700
Data Index: 5795194 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.7337. Min Act: -0.1700
Data Index: 7927574 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.7337. Min Act: -0.1700
Data Index: 313438 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.6711. Min Act: -0.1700
Data Index: 7514829 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.6867. Min Act: -0.1700
Data Index: 5519277 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.6398. Min Act: -0.1700
Data Index: 8247501 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.6242. Min Act: -0.1700
Data Index: 3545371 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.6085. Min Act: -0.1700
Data Index: 672280 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.6242. Min Act: -0.1700
Data Index: 8813754 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.6242. Min Act: -0.1700
Data Index: 4972797 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.6242. Min Act: -0.1700
Data Index: 8543040 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.6242. Min Act: -0.1700
Data Index: 1743795 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.6085. Min Act: -0.1700
Data Index: 2568972 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.5772. Min Act: -0.1700
Data Index: 6792280 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.5616. Min Act: -0.1700
Data Index: 4721865 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.5616. Min Act: -0.1700
Data Index: 5693431 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9057. Min Range: -3.9057
Max Act: 3.5772. Min Act: -0.1700
Data Index: 502165 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19