Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1718 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.8517. Min Act: -0.1700
Data Index: 6856283 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.7892. Min Act: -0.1700
Data Index: 7008462 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.8204. Min Act: -0.1700
Data Index: 8197855 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.7579. Min Act: -0.1700
Data Index: 5313598 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.6642. Min Act: -0.1700
Data Index: 1967162 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.6329. Min Act: -0.1700
Data Index: 6769925 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.6329. Min Act: -0.1700
Data Index: 4558480 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.6017. Min Act: -0.1700
Data Index: 205916 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.6017. Min Act: -0.1700
Data Index: 7052991 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.6017. Min Act: -0.1700
Data Index: 3696017 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.5704. Min Act: -0.1700
Data Index: 481416 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.5704. Min Act: -0.1700
Data Index: 2306657 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.5704. Min Act: -0.1700
Data Index: 5237658 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.5704. Min Act: -0.1700
Data Index: 1792511 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.5392. Min Act: -0.1700
Data Index: 5858831 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.5392. Min Act: -0.1700
Data Index: 2793949 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.5392. Min Act: -0.1700
Data Index: 956491 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.5079. Min Act: -0.1700
Data Index: 4177193 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.5079. Min Act: -0.1700
Data Index: 1870518 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8517. Min Range: -5.8517
Max Act: 5.5079. Min Act: -0.1700
Data Index: 5038569 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19