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

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

Neuron 1058 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0402. Min Act: -0.0000

Data Index: 151725 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1526737 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0357. Min Act: -0.0000

Data Index: 102224 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1641000 (Python Code)

Max Activating Token Index: 636

Text #4

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0357. Min Act: -0.0000

Data Index: 252745 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0339. Min Act: -0.0000

Data Index: 216388 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0334. Min Act: -0.0000

Data Index: 832058 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0317. Min Act: -0.0000

Data Index: 629485 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0332. Min Act: -0.0000

Data Index: 728812 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0344. Min Act: -0.0000

Data Index: 498570 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0335. Min Act: -0.0000

Data Index: 73271 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1429197 (Python Code)

Max Activating Token Index: 428

Text #12

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0325. Min Act: -0.0000

Data Index: 162216 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0306. Min Act: -0.0000

Data Index: 639101 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0308. Min Act: -0.0000

Data Index: 763689 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0300. Min Act: -0.0000

Data Index: 1239328 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0296. Min Act: -0.0000

Data Index: 600823 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0293. Min Act: -0.0000

Data Index: 717909 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0290. Min Act: -0.0000

Data Index: 814968 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0284. Min Act: -0.0000

Data Index: 1380856 (Python Code)

Max Activating Token Index: 149