Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0991. Min Range: -5.0991
Max Act: 5.0991. Min Act: -0.1700
Data Index: 5739558 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0991. Min Range: -5.0991
Max Act: 5.0366. Min Act: -0.1700
Data Index: 1068778 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.8804. Min Act: -0.1700
Data Index: 3812683 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.5679. Min Act: -0.1700
Data Index: 2127339 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.5210. Min Act: -0.1700
Data Index: 3086595 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.4272. Min Act: -0.1700
Data Index: 8079191 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.4741. Min Act: -0.1700
Data Index: 6145500 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.4272. Min Act: -0.1700
Data Index: 7698054 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.4272. Min Act: -0.1700
Data Index: 718311 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.4272. Min Act: -0.1700
Data Index: 1553437 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.4116. Min Act: -0.1700
Data Index: 2961528 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.3960. Min Act: -0.1700
Data Index: 6191798 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.3960. Min Act: -0.1700
Data Index: 3833386 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.3960. Min Act: -0.1700
Data Index: 1736513 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.3491. Min Act: -0.1700
Data Index: 2893501 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.3647. Min Act: -0.1700
Data Index: 7291520 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.4272. Min Act: -0.1700
Data Index: 3706070 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.3491. Min Act: -0.1700
Data Index: 787285 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.4116. Min Act: -0.1700
Data Index: 2691319 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0991. Min Range: -5.0991
Max Act: 4.3491. Min Act: -0.1700
Data Index: 6260000 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19