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

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

Neuron 2686 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: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1276916 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0183. Min Act: -0.0003

Data Index: 324128 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0179. Min Act: -0.0003

Data Index: 305617 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0178. Min Act: -0.0003

Data Index: 675123 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1309380 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0172. Min Act: -0.0003

Data Index: 895820 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0173. Min Act: -0.0002

Data Index: 358780 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0170. Min Act: -0.0003

Data Index: 941299 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0164. Min Act: -0.0002

Data Index: 146556 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0159. Min Act: -0.0003

Data Index: 264483 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0158. Min Act: -0.0003

Data Index: 211073 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0155. Min Act: -0.0003

Data Index: 760065 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0156. Min Act: -0.0003

Data Index: 979833 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0156. Min Act: -0.0002

Data Index: 3175 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1090404 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1075415 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0153. Min Act: -0.0002

Data Index: 517756 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0151. Min Act: -0.0003

Data Index: 271045 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1238724 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0146. Min Act: -0.0003

Data Index: 290559 (C4 (Web Text))

Max Activating Token Index: 465