Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1551 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4363. Min Act: -0.1700
Data Index: 5028178 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4050. Min Act: -0.1700
Data Index: 4706335 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4050. Min Act: -0.1700
Data Index: 6246460 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3738. Min Act: -0.1700
Data Index: 6915758 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3738. Min Act: -0.1700
Data Index: 6022779 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3113. Min Act: -0.1700
Data Index: 7818323 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3425. Min Act: -0.1700
Data Index: 2609228 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3425. Min Act: -0.1700
Data Index: 3128871 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3113. Min Act: -0.1700
Data Index: 4383014 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3113. Min Act: -0.1700
Data Index: 5258807 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2800. Min Act: -0.1700
Data Index: 8399452 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3113. Min Act: -0.1700
Data Index: 8573680 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3113. Min Act: -0.1700
Data Index: 6485842 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2800. Min Act: -0.1700
Data Index: 4905768 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2800. Min Act: -0.1700
Data Index: 6606243 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2800. Min Act: -0.1700
Data Index: 5524790 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2800. Min Act: -0.1700
Data Index: 8348343 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 596993 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2800. Min Act: -0.1700
Data Index: 2911428 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 1654661 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19