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

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

Neuron 4025 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0461. Min Act: -0.0003

Data Index: 154640 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0396. Min Act: -0.0003

Data Index: 847499 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0418. Min Act: -0.0003

Data Index: 899408 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1129732 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1209507 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0386. Min Act: -0.0003

Data Index: 273017 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1068933 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1151400 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0334. Min Act: -0.0003

Data Index: 223181 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1223131 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1246032 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1076701 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0344. Min Act: -0.0003

Data Index: 643563 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0327. Min Act: -0.0003

Data Index: 89641 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0330. Min Act: -0.0003

Data Index: 541927 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0343. Min Act: -0.0003

Data Index: 526974 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0332. Min Act: -0.0003

Data Index: 620013 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0312. Min Act: -0.0003

Data Index: 712055 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0324. Min Act: -0.0003

Data Index: 141134 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.0461. Min Range: -0.0461

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1028190 (C4 (Web Text))

Max Activating Token Index: 290