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

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

Neuron 4431 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0380. Min Act: -0.0002

Data Index: 330436 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0348. Min Act: -0.0002

Data Index: 569472 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1136094 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0367. Min Act: -0.0002

Data Index: 478187 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0358. Min Act: -0.0003

Data Index: 362298 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0399. Min Act: -0.0002

Data Index: 874368 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0341. Min Act: -0.0002

Data Index: 90784 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0365. Min Act: -0.0002

Data Index: 29267 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0377. Min Act: -0.0002

Data Index: 385667 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1234352 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0316. Min Act: -0.0002

Data Index: 233160 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0358. Min Act: -0.0002

Data Index: 898699 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1220124 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0362. Min Act: -0.0002

Data Index: 759803 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1160303 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0002

Data Index: 521858 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0323. Min Act: -0.0002

Data Index: 432587 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0324. Min Act: -0.0002

Data Index: 810614 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0336. Min Act: -0.0002

Data Index: 530743 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1069508 (C4 (Web Text))

Max Activating Token Index: 505