Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 522 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0429. Min Act: -0.0001

Data Index: 1543335 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1215478 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0413. Min Act: -0.0001

Data Index: 738341 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0418. Min Act: -0.0001

Data Index: 1128176 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0378. Min Act: -0.0001

Data Index: 742045 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0372. Min Act: -0.0002

Data Index: 1507543 (Python Code)

Max Activating Token Index: 361

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1425909 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1230442 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0379. Min Act: -0.0001

Data Index: 1436249 (Python Code)

Max Activating Token Index: 662

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1515356 (Python Code)

Max Activating Token Index: 791

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1579329 (Python Code)

Max Activating Token Index: 559

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1576878 (Python Code)

Max Activating Token Index: 622

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1470287 (Python Code)

Max Activating Token Index: 497

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0384. Min Act: -0.0001

Data Index: 763233 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1637935 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1433071 (Python Code)

Max Activating Token Index: 460

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1421286 (Python Code)

Max Activating Token Index: 463

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1556493 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1456551 (Python Code)

Max Activating Token Index: 658

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1451687 (Python Code)

Max Activating Token Index: 804