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

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

Neuron 5 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: 0.1545. Min Range: -0.1545

Max Act: 0.1545. Min Act: -0.0003

Data Index: 1230045 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1527. Min Act: -0.0003

Data Index: 1337552 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1395. Min Act: -0.0003

Data Index: 1064853 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1341. Min Act: -0.0003

Data Index: 436041 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1361. Min Act: -0.0003

Data Index: 461912 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1408. Min Act: -0.0003

Data Index: 385159 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1302. Min Act: -0.0004

Data Index: 165393 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1341. Min Act: -0.0003

Data Index: 1283687 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1315. Min Act: -0.0003

Data Index: 1324679 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1342. Min Act: -0.0003

Data Index: 14635 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1282. Min Act: -0.0003

Data Index: 712305 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1295. Min Act: -0.0003

Data Index: 391066 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1241. Min Act: -0.0003

Data Index: 499661 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1272. Min Act: -0.0003

Data Index: 5367 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1278. Min Act: -0.0003

Data Index: 252457 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1266. Min Act: -0.0004

Data Index: 1049222 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1220. Min Act: -0.0003

Data Index: 127243 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1228. Min Act: -0.0003

Data Index: 662014 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1170. Min Act: -0.0003

Data Index: 139151 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.1545. Min Range: -0.1545

Max Act: 0.1210. Min Act: -0.0003

Data Index: 470706 (C4 (Web Text))

Max Activating Token Index: 475