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

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

Neuron 5775 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0002

Data Index: 833649 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0481. Min Act: -0.0002

Data Index: 556122 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0446. Min Act: -0.0002

Data Index: 454686 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0446. Min Act: -0.0002

Data Index: 605363 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1315535 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0397. Min Act: -0.0002

Data Index: 155680 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1330854 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0389. Min Act: -0.0002

Data Index: 941097 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0379. Min Act: -0.0002

Data Index: 903173 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0382. Min Act: -0.0002

Data Index: 11730 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0369. Min Act: -0.0002

Data Index: 59062 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0358. Min Act: -0.0002

Data Index: 578616 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1038516 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1010219 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0346. Min Act: -0.0002

Data Index: 709616 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0353. Min Act: -0.0002

Data Index: 601156 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0349. Min Act: -0.0002

Data Index: 484475 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0353. Min Act: -0.0002

Data Index: 240735 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1133056 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0358. Min Act: -0.0002

Data Index: 978965 (C4 (Web Text))

Max Activating Token Index: 680