Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1599 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1555. Min Act: -0.0003

Data Index: 898849 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1388. Min Act: -0.0002

Data Index: 369442 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1360. Min Act: -0.0002

Data Index: 1097142 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1244. Min Act: -0.0002

Data Index: 811338 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1233. Min Act: -0.0003

Data Index: 781361 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1231. Min Act: -0.0003

Data Index: 125276 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1241. Min Act: -0.0003

Data Index: 486097 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1234. Min Act: -0.0003

Data Index: 207821 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1169. Min Act: -0.0002

Data Index: 665662 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1123. Min Act: -0.0003

Data Index: 459920 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1105. Min Act: -0.0003

Data Index: 132335 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1214. Min Act: -0.0003

Data Index: 68484 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1077. Min Act: -0.0003

Data Index: 726795 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1122. Min Act: -0.0002

Data Index: 573703 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1110. Min Act: -0.0002

Data Index: 401336 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1108. Min Act: -0.0002

Data Index: 60060 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1141. Min Act: -0.0003

Data Index: 427364 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1092. Min Act: -0.0002

Data Index: 716938 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1054. Min Act: -0.0004

Data Index: 206608 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.1555. Min Range: -0.1555

Max Act: 0.1051. Min Act: -0.0003

Data Index: 264339 (C4 (Web Text))

Max Activating Token Index: 512