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

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

Neuron 3250 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: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1187381 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1302965 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0229. Min Act: -0.0002

Data Index: 618342 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0201. Min Act: -0.0002

Data Index: 954182 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1295785 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0162. Min Act: -0.0002

Data Index: 129427 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0167. Min Act: -0.0002

Data Index: 557979 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1155148 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0195. Min Act: -0.0002

Data Index: 320778 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1311157 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0179. Min Act: -0.0002

Data Index: 51079 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0161. Min Act: -0.0002

Data Index: 416182 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1099794 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1043527 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0182. Min Act: -0.0002

Data Index: 767065 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0152. Min Act: -0.0002

Data Index: 624693 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0167. Min Act: -0.0002

Data Index: 918984 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0164. Min Act: -0.0002

Data Index: 28187 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0173. Min Act: -0.0002

Data Index: 374547 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0166. Min Act: -0.0002

Data Index: 354670 (C4 (Web Text))

Max Activating Token Index: 907