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

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

Neuron 3553 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0002

Data Index: 416556 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0408. Min Act: -0.0002

Data Index: 810250 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1034640 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0385. Min Act: -0.0001

Data Index: 354044 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0370. Min Act: -0.0001

Data Index: 490631 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0380. Min Act: -0.0001

Data Index: 696541 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0391. Min Act: -0.0002

Data Index: 581033 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1074606 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1136865 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0353. Min Act: -0.0001

Data Index: 46825 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0368. Min Act: -0.0002

Data Index: 731057 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0348. Min Act: -0.0002

Data Index: 171411 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0357. Min Act: -0.0001

Data Index: 823486 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0360. Min Act: -0.0002

Data Index: 644566 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0338. Min Act: -0.0001

Data Index: 564210 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0325. Min Act: -0.0001

Data Index: 580281 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1076254 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0344. Min Act: -0.0002

Data Index: 448076 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0349. Min Act: -0.0001

Data Index: 718914 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0359. Min Act: -0.0001

Data Index: 38830 (C4 (Web Text))

Max Activating Token Index: 641