Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2963 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0004

Data Index: 957916 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0486. Min Act: -0.0004

Data Index: 498160 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0357. Min Act: -0.0004

Data Index: 236508 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0388. Min Act: -0.0004

Data Index: 767927 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0356. Min Act: -0.0004

Data Index: 491309 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0357. Min Act: -0.0004

Data Index: 1000731 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0347. Min Act: -0.0004

Data Index: 421336 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0345. Min Act: -0.0004

Data Index: 1203461 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0352. Min Act: -0.0004

Data Index: 154100 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0352. Min Act: -0.0004

Data Index: 1078815 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0335. Min Act: -0.0004

Data Index: 122226 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0336. Min Act: -0.0004

Data Index: 1241308 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0326. Min Act: -0.0004

Data Index: 266963 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0320. Min Act: -0.0004

Data Index: 1010056 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0322. Min Act: -0.0004

Data Index: 394982 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0322. Min Act: -0.0004

Data Index: 776663 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0332. Min Act: -0.0004

Data Index: 167472 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0353. Min Act: -0.0004

Data Index: 1218641 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0329. Min Act: -0.0004

Data Index: 1087730 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0323. Min Act: -0.0004

Data Index: 1198264 (C4 (Web Text))

Max Activating Token Index: 958