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

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

Neuron 1072 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.9563. Min Act: -0.0000

Data Index: 992564 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.9323. Min Act: -0.0000

Data Index: 521711 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8695. Min Act: -0.0000

Data Index: 582249 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6561. Min Act: -0.0000

Data Index: 462742 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5902. Min Act: -0.0000

Data Index: 339106 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6243. Min Act: -0.0000

Data Index: 779384 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6060. Min Act: -0.0000

Data Index: 550330 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6163. Min Act: -0.0000

Data Index: 448853 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5851. Min Act: -0.0000

Data Index: 416393 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5780. Min Act: -0.0000

Data Index: 393946 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1146990 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1302923 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5561. Min Act: -0.0000

Data Index: 50994 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5698. Min Act: -0.0000

Data Index: 884611 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5839. Min Act: -0.0000

Data Index: 347305 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5216. Min Act: -0.0000

Data Index: 90168 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5975. Min Act: -0.0000

Data Index: 257925 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5490. Min Act: -0.0000

Data Index: 328682 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5370. Min Act: 0.0000

Data Index: 168470 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.5264. Min Act: 0.0000

Data Index: 679169 (C4 (Web Text))

Max Activating Token Index: 515