Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5136 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1449637 (Python Code)

Max Activating Token Index: 472

Text #1

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0353. Min Act: -0.0001

Data Index: 601430 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1451796 (Python Code)

Max Activating Token Index: 896

Text #3

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1258984 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1106995 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0330. Min Act: -0.0001

Data Index: 18553 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0323. Min Act: -0.0001

Data Index: 828507 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1445458 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0329. Min Act: -0.0001

Data Index: 231623 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0311. Min Act: -0.0001

Data Index: 114611 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0324. Min Act: -0.0001

Data Index: 489942 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1063908 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0331. Min Act: -0.0001

Data Index: 845792 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1423729 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0326. Min Act: -0.0001

Data Index: 558961 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0327. Min Act: -0.0001

Data Index: 1230699 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0279. Min Act: -0.0001

Data Index: 958842 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0309. Min Act: -0.0001

Data Index: 460682 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0286. Min Act: -0.0001

Data Index: 719336 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0304. Min Act: -0.0001

Data Index: 317542 (C4 (Web Text))

Max Activating Token Index: 315