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

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

Neuron 4200 in Layer 0

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: 0.0208. Min Act: -0.0002

Data Index: 1192 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0184. Min Act: -0.0002

Data Index: 213744 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0176. Min Act: -0.0002

Data Index: 921059 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1087485 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1230509 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0161. Min Act: -0.0002

Data Index: 122885 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0159. Min Act: -0.0002

Data Index: 746520 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1231819 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0154. Min Act: -0.0002

Data Index: 367620 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0154. Min Act: -0.0002

Data Index: 309947 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0154. Min Act: -0.0002

Data Index: 70380 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1239319 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0154. Min Act: -0.0002

Data Index: 25277 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0151. Min Act: -0.0002

Data Index: 836499 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0150. Min Act: -0.0002

Data Index: 658909 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0149. Min Act: -0.0002

Data Index: 18610 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0149. Min Act: -0.0002

Data Index: 911409 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0148. Min Act: -0.0002

Data Index: 1309611 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0148. Min Act: -0.0002

Data Index: 216813 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0208. Min Range: -0.0208

Max Act: 0.0148. Min Act: -0.0002

Data Index: 926815 (C4 (Web Text))

Max Activating Token Index: 18