Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1858 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.6426. Min Range: -10.6426
Max Act: 10.6426. Min Act: -0.1700
Data Index: 8008334 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6426. Min Range: -10.6426
Max Act: 10.0801. Min Act: -0.1700
Data Index: 3480816 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.7051. Min Act: -0.1700
Data Index: 2269495 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.5176. Min Act: -0.1700
Data Index: 6903891 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.5176. Min Act: -0.1700
Data Index: 1385745 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.5176. Min Act: -0.1700
Data Index: 7525458 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.4551. Min Act: -0.1700
Data Index: 738616 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.3926. Min Act: -0.1700
Data Index: 738615 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.3926. Min Act: -0.1700
Data Index: 4571560 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.2051. Min Act: -0.1700
Data Index: 898127 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.2051. Min Act: -0.1700
Data Index: 5111662 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.1426. Min Act: -0.1700
Data Index: 502691 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.2051. Min Act: -0.1700
Data Index: 7917171 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.2051. Min Act: -0.1700
Data Index: 1900803 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.2051. Min Act: -0.1700
Data Index: 4676650 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.1426. Min Act: -0.1700
Data Index: 2164974 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.0801. Min Act: -0.1700
Data Index: 564457 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.2051. Min Act: -0.1700
Data Index: 4189431 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.0801. Min Act: -0.1700
Data Index: 725730 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6426. Min Range: -10.6426
Max Act: 9.0176. Min Act: -0.1700
Data Index: 4587977 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19