Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 672 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1297. Min Act: -0.0002

Data Index: 1096554 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1237. Min Act: -0.0002

Data Index: 916969 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1145. Min Act: -0.0002

Data Index: 914497 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1187. Min Act: -0.0002

Data Index: 195590 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1171. Min Act: -0.0002

Data Index: 86410 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1196. Min Act: -0.0002

Data Index: 1278101 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1218. Min Act: -0.0002

Data Index: 848735 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1191. Min Act: -0.0002

Data Index: 552571 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1143. Min Act: -0.0002

Data Index: 680430 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1155. Min Act: -0.0002

Data Index: 536475 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1158. Min Act: -0.0002

Data Index: 207203 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1201785 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1124. Min Act: -0.0002

Data Index: 454268 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1176. Min Act: -0.0002

Data Index: 795610 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1175. Min Act: -0.0002

Data Index: 401083 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1148. Min Act: -0.0002

Data Index: 290909 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1117. Min Act: -0.0002

Data Index: 143474 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1117613 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1149. Min Act: -0.0002

Data Index: 26422 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1160. Min Act: -0.0002

Data Index: 1244566 (C4 (Web Text))

Max Activating Token Index: 609