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

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

Neuron 1966 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: 0.1302. Min Range: -0.1302

Max Act: 0.1194. Min Act: -0.0002

Data Index: 752709 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1288. Min Act: -0.0002

Data Index: 344018 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1302. Min Act: -0.0002

Data Index: 948861 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1209. Min Act: -0.0002

Data Index: 886608 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1322258 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1218. Min Act: -0.0002

Data Index: 36089 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1228. Min Act: -0.0002

Data Index: 698774 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1010470 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1184. Min Act: -0.0002

Data Index: 767946 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1033. Min Act: -0.0002

Data Index: 192658 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1049. Min Act: -0.0002

Data Index: 688977 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1030. Min Act: -0.0002

Data Index: 1082899 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1114. Min Act: -0.0002

Data Index: 563142 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1129. Min Act: -0.0002

Data Index: 26686 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1039. Min Act: -0.0002

Data Index: 948383 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1320463 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0966. Min Act: -0.0002

Data Index: 513893 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1271076 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1175213 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1013. Min Act: -0.0002

Data Index: 474386 (C4 (Web Text))

Max Activating Token Index: 105