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

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

Neuron 36 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: 0.0427. Min Range: -0.0427

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1041357 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0363. Min Act: -0.0001

Data Index: 509614 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0374. Min Act: -0.0001

Data Index: 1171239 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0401. Min Act: -0.0001

Data Index: 1141621 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0375. Min Act: -0.0001

Data Index: 787545 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0372. Min Act: -0.0001

Data Index: 491551 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0366. Min Act: -0.0001

Data Index: 1195938 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0356. Min Act: -0.0001

Data Index: 978552 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0333. Min Act: -0.0001

Data Index: 423895 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0351. Min Act: -0.0001

Data Index: 1106320 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0348. Min Act: -0.0001

Data Index: 645085 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0340. Min Act: -0.0001

Data Index: 473503 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0333. Min Act: -0.0001

Data Index: 213486 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0327. Min Act: -0.0001

Data Index: 894959 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0339. Min Act: -0.0001

Data Index: 915809 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0339. Min Act: -0.0001

Data Index: 529229 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0322. Min Act: -0.0001

Data Index: 95398 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0312. Min Act: -0.0001

Data Index: 95501 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1299419 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0427. Min Range: -0.0427

Max Act: 0.0298. Min Act: -0.0001

Data Index: 804289 (C4 (Web Text))

Max Activating Token Index: 395