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

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

Neuron 2385 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1631613 (Python Code)

Max Activating Token Index: 309

Text #1

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0409. Min Act: -0.0001

Data Index: 259314 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1108473 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0367. Min Act: -0.0001

Data Index: 643105 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0396. Min Act: -0.0001

Data Index: 143763 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0391. Min Act: -0.0001

Data Index: 328597 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0323. Min Act: -0.0001

Data Index: 33933 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0363. Min Act: -0.0001

Data Index: 11698 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1039738 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1539984 (Python Code)

Max Activating Token Index: 604

Text #10

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0341. Min Act: -0.0001

Data Index: 708278 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0320. Min Act: -0.0001

Data Index: 382433 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1212526 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0287. Min Act: -0.0001

Data Index: 583830 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0307. Min Act: -0.0001

Data Index: 615454 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0342. Min Act: -0.0001

Data Index: 108542 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0301. Min Act: -0.0001

Data Index: 854019 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0319. Min Act: -0.0001

Data Index: 854831 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0293. Min Act: -0.0001

Data Index: 857119 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1073221 (C4 (Web Text))

Max Activating Token Index: 582