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

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

Neuron 3282 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3095. Min Range: -1.3095

Max Act: 1.2989. Min Act: -0.0002

Data Index: 910335 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 1.3095. Min Range: -1.3095

Max Act: 1.3095. Min Act: -0.0002

Data Index: 1086014 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.3095. Min Range: -1.3095

Max Act: 1.1854. Min Act: -0.0002

Data Index: 1102725 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 1.3095. Min Range: -1.3095

Max Act: 1.1297. Min Act: -0.0002

Data Index: 967007 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 1.3095. Min Range: -1.3095

Max Act: 1.0667. Min Act: -0.0002

Data Index: 1280450 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 1.3095. Min Range: -1.3095

Max Act: 1.0852. Min Act: -0.0002

Data Index: 762134 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 1.3095. Min Range: -1.3095

Max Act: 1.0524. Min Act: -0.0002

Data Index: 1158291 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 1.3095. Min Range: -1.3095

Max Act: 0.9434. Min Act: -0.0002

Data Index: 816483 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.3095. Min Range: -1.3095

Max Act: 1.0451. Min Act: -0.0002

Data Index: 937500 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 1.3095. Min Range: -1.3095

Max Act: 0.9860. Min Act: -0.0002

Data Index: 322201 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 1.3095. Min Range: -1.3095

Max Act: 0.9251. Min Act: -0.0002

Data Index: 1007054 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 1.3095. Min Range: -1.3095

Max Act: 0.9637. Min Act: -0.0002

Data Index: 696630 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 1.3095. Min Range: -1.3095

Max Act: 0.9634. Min Act: -0.0002

Data Index: 76810 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 1.3095. Min Range: -1.3095

Max Act: 0.9294. Min Act: -0.0002

Data Index: 706986 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.3095. Min Range: -1.3095

Max Act: 0.9575. Min Act: -0.0002

Data Index: 938907 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 1.3095. Min Range: -1.3095

Max Act: 0.9788. Min Act: -0.0002

Data Index: 821867 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 1.3095. Min Range: -1.3095

Max Act: 0.9780. Min Act: -0.0002

Data Index: 310712 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 1.3095. Min Range: -1.3095

Max Act: 0.9609. Min Act: -0.0002

Data Index: 416958 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 1.3095. Min Range: -1.3095

Max Act: 0.9352. Min Act: -0.0002

Data Index: 1144735 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 1.3095. Min Range: -1.3095

Max Act: 1.0086. Min Act: -0.0002

Data Index: 623373 (C4 (Web Text))

Max Activating Token Index: 1014