Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 584 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1355934 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1599. Min Act: -0.0002

Data Index: 426380 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1540096 (Python Code)

Max Activating Token Index: 65

Text #3

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1595. Min Act: -0.0002

Data Index: 744432 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1597. Min Act: -0.0001

Data Index: 949863 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1355. Min Act: -0.0001

Data Index: 407430 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1328. Min Act: -0.0001

Data Index: 330713 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1195. Min Act: -0.0002

Data Index: 154923 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1329. Min Act: -0.0001

Data Index: 194217 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1266. Min Act: -0.0002

Data Index: 829974 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1212. Min Act: -0.0001

Data Index: 169734 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1434. Min Act: -0.0002

Data Index: 415276 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1086. Min Act: -0.0002

Data Index: 1167322 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1519042 (Python Code)

Max Activating Token Index: 389

Text #14

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1322. Min Act: -0.0001

Data Index: 339 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1139. Min Act: -0.0002

Data Index: 298162 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1257. Min Act: -0.0002

Data Index: 973103 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1065. Min Act: -0.0001

Data Index: 345427 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1208. Min Act: -0.0002

Data Index: 482466 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.1599. Min Range: -0.1599

Max Act: 0.1277. Min Act: -0.0001

Data Index: 182911 (C4 (Web Text))

Max Activating Token Index: 614