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

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

Neuron 2639 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: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0002

Data Index: 419023 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1236258 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0987. Min Act: -0.0002

Data Index: 450808 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0988. Min Act: -0.0002

Data Index: 19312 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0999. Min Act: -0.0002

Data Index: 345516 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0990. Min Act: -0.0002

Data Index: 448185 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0995. Min Act: -0.0002

Data Index: 858248 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1479867 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1292034 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0740. Min Act: -0.0002

Data Index: 615120 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1010. Min Act: -0.0002

Data Index: 337386 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0867. Min Act: -0.0002

Data Index: 103549 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1319531 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1034296 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1237407 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0725. Min Act: -0.0002

Data Index: 551186 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1093688 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0880. Min Act: -0.0002

Data Index: 968374 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1036177 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0939. Min Act: -0.0002

Data Index: 999120 (C4 (Web Text))

Max Activating Token Index: 364