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

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

Neuron 5104 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: 0.0207. Min Range: -0.0207

Max Act: 0.0207. Min Act: -0.0002

Data Index: 627138 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1117604 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0187. Min Act: -0.0002

Data Index: 693452 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0177. Min Act: -0.0002

Data Index: 907737 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0185. Min Act: -0.0002

Data Index: 485890 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0154. Min Act: -0.0002

Data Index: 680260 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0162. Min Act: -0.0002

Data Index: 904131 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0159. Min Act: -0.0002

Data Index: 109480 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1357002 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0164. Min Act: -0.0002

Data Index: 401249 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0181. Min Act: -0.0002

Data Index: 935894 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0159. Min Act: -0.0002

Data Index: 833190 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0157. Min Act: -0.0002

Data Index: 646524 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1195108 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0167. Min Act: -0.0002

Data Index: 863930 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0153. Min Act: -0.0002

Data Index: 1168798 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0168. Min Act: -0.0002

Data Index: 10889 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1149684 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0157. Min Act: -0.0002

Data Index: 44230 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0163. Min Act: -0.0002

Data Index: 160989 (C4 (Web Text))

Max Activating Token Index: 338