Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5629 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1606733 (Python Code)

Max Activating Token Index: 121

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1405122 (Python Code)

Max Activating Token Index: 510

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1436346 (Python Code)

Max Activating Token Index: 604

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1357252 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0183. Min Act: -0.0002

Data Index: 1453785 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0182. Min Act: -0.0002

Data Index: 581719 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0166. Min Act: -0.0002

Data Index: 129048 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1395694 (Python Code)

Max Activating Token Index: 222

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0161. Min Act: -0.0002

Data Index: 835718 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1195744 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1095789 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1511188 (Python Code)

Max Activating Token Index: 81

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1441675 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1384010 (Python Code)

Max Activating Token Index: 712

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1542737 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1038383 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0160. Min Act: -0.0002

Data Index: 144682 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1191567 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1404570 (Python Code)

Max Activating Token Index: 607

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1364805 (Python Code)

Max Activating Token Index: 7