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

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

Neuron 4530 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0187. Min Act: -0.0003

Data Index: 879042 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0204. Min Act: -0.0002

Data Index: 549735 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1532640 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1252628 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0199. Min Act: -0.0003

Data Index: 507613 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1042427 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0175. Min Act: -0.0003

Data Index: 615372 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0203. Min Act: -0.0003

Data Index: 753296 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1256771 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0196. Min Act: -0.0002

Data Index: 75614 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0144. Min Act: -0.0003

Data Index: 828827 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0170. Min Act: -0.0003

Data Index: 514134 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0185. Min Act: -0.0002

Data Index: 99489 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1422914 (Python Code)

Max Activating Token Index: 247

Text #14

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0160. Min Act: -0.0003

Data Index: 121420 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0144. Min Act: -0.0003

Data Index: 549610 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1198066 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0164. Min Act: -0.0002

Data Index: 80185 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0171. Min Act: -0.0003

Data Index: 758232 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1638676 (Python Code)

Max Activating Token Index: 49