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

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

Neuron 1513 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: 0.1316. Min Range: -0.1316

Max Act: 0.1316. Min Act: -0.0002

Data Index: 358223 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1176. Min Act: -0.0001

Data Index: 260776 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1180. Min Act: -0.0002

Data Index: 442701 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1152. Min Act: -0.0002

Data Index: 359773 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1169. Min Act: -0.0002

Data Index: 978078 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1121. Min Act: -0.0001

Data Index: 363627 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1152. Min Act: -0.0002

Data Index: 750769 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1182288 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1293283 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1062. Min Act: -0.0002

Data Index: 905373 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1091. Min Act: -0.0002

Data Index: 895842 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1215883 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1089. Min Act: -0.0002

Data Index: 830128 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1119. Min Act: -0.0002

Data Index: 55796 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1016613 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0986. Min Act: -0.0002

Data Index: 426086 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1031. Min Act: -0.0002

Data Index: 590298 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1034. Min Act: -0.0002

Data Index: 787646 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1312179 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1019. Min Act: -0.0001

Data Index: 851461 (C4 (Web Text))

Max Activating Token Index: 981