Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 765 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0813. Min Range: -1.0813

Max Act: 1.0813. Min Act: -0.0000

Data Index: 455590 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7268. Min Act: -0.0000

Data Index: 685742 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7013. Min Act: -0.0000

Data Index: 594197 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1249404 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1016066 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1050081 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6450. Min Act: -0.0000

Data Index: 403502 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6266. Min Act: -0.0000

Data Index: 410900 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6535. Min Act: -0.0000

Data Index: 164908 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.5977. Min Act: -0.0000

Data Index: 165663 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6243. Min Act: -0.0000

Data Index: 284319 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1237246 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6223. Min Act: -0.0000

Data Index: 487594 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.5925. Min Act: -0.0000

Data Index: 228286 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6114. Min Act: -0.0000

Data Index: 826331 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6074. Min Act: -0.0000

Data Index: 797609 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6257. Min Act: -0.0000

Data Index: 41970 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1209264 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1080971 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 1.0813. Min Range: -1.0813

Max Act: 0.6267. Min Act: -0.0000

Data Index: 160579 (C4 (Web Text))

Max Activating Token Index: 971