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

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

Neuron 1422 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1424563 (Python Code)

Max Activating Token Index: 577

Text #1

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1396577 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1388604 (Python Code)

Max Activating Token Index: 190

Text #3

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0392. Min Act: -0.0003

Data Index: 700175 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1418828 (Python Code)

Max Activating Token Index: 472

Text #5

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1398555 (Python Code)

Max Activating Token Index: 165

Text #6

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1367513 (Python Code)

Max Activating Token Index: 220

Text #7

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1585361 (Python Code)

Max Activating Token Index: 697

Text #8

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1436595 (Python Code)

Max Activating Token Index: 833

Text #9

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0336. Min Act: -0.0003

Data Index: 498474 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1015043 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1410887 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1617168 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0313. Min Act: -0.0002

Data Index: 452050 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1484725 (Python Code)

Max Activating Token Index: 931

Text #15

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1405842 (Python Code)

Max Activating Token Index: 597

Text #16

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1505357 (Python Code)

Max Activating Token Index: 371

Text #17

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1654771 (Python Code)

Max Activating Token Index: 819

Text #18

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1585108 (Python Code)

Max Activating Token Index: 497

Text #19

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0291. Min Act: -0.0002

Data Index: 24425 (C4 (Web Text))

Max Activating Token Index: 41