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

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

Neuron 3621 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: 0.1368. Min Range: -0.1368

Max Act: 0.1189. Min Act: -0.0002

Data Index: 1116003 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1368. Min Act: -0.0002

Data Index: 615496 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1213. Min Act: -0.0002

Data Index: 1146070 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1204. Min Act: -0.0002

Data Index: 655847 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1130. Min Act: -0.0002

Data Index: 448597 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1112. Min Act: -0.0002

Data Index: 508292 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1062. Min Act: -0.0002

Data Index: 757102 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1018277 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1020. Min Act: -0.0002

Data Index: 39883 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1261850 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1021006 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1024643 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1311. Min Act: -0.0002

Data Index: 81138 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1176. Min Act: -0.0002

Data Index: 541489 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1149. Min Act: -0.0002

Data Index: 696148 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1077. Min Act: -0.0002

Data Index: 53015 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.0894. Min Act: -0.0002

Data Index: 123508 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1057. Min Act: -0.0002

Data Index: 201869 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1167. Min Act: -0.0002

Data Index: 641405 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.1368. Min Range: -0.1368

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1176207 (C4 (Web Text))

Max Activating Token Index: 37