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

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

Neuron 1787 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1047644 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1664. Min Act: -0.0001

Data Index: 467753 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1472. Min Act: -0.0001

Data Index: 61891 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1351657 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1334441 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1287. Min Act: -0.0001

Data Index: 313429 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1246. Min Act: -0.0001

Data Index: 358479 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1202632 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1322. Min Act: -0.0001

Data Index: 543007 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1225955 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1167. Min Act: -0.0001

Data Index: 18948 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1126. Min Act: -0.0001

Data Index: 822210 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1198. Min Act: -0.0001

Data Index: 935094 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1313848 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1237. Min Act: -0.0001

Data Index: 869515 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1099. Min Act: -0.0001

Data Index: 881154 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1257498 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1201. Min Act: -0.0001

Data Index: 854244 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1016. Min Act: -0.0001

Data Index: 371349 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1155. Min Act: -0.0001

Data Index: 701491 (C4 (Web Text))

Max Activating Token Index: 656