Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 222 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1575687 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0374. Min Act: -0.0004

Data Index: 101241 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1274447 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0342. Min Act: -0.0004

Data Index: 366808 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1461772 (Python Code)

Max Activating Token Index: 981

Text #5

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1027506 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0361. Min Act: -0.0003

Data Index: 666420 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1517567 (Python Code)

Max Activating Token Index: 766

Text #8

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0355. Min Act: -0.0003

Data Index: 488225 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0348. Min Act: -0.0003

Data Index: 831162 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0344. Min Act: -0.0002

Data Index: 613371 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1620327 (Python Code)

Max Activating Token Index: 871

Text #12

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0351. Min Act: -0.0003

Data Index: 973203 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0351. Min Act: -0.0003

Data Index: 764359 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0339. Min Act: -0.0003

Data Index: 794365 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1585763 (Python Code)

Max Activating Token Index: 129

Text #16

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0347. Min Act: -0.0003

Data Index: 493472 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1495786 (Python Code)

Max Activating Token Index: 320

Text #18

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1475968 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1627351 (Python Code)

Max Activating Token Index: 616