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

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

Neuron 2418 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: 0.0537. Min Range: -0.0537

Max Act: 0.0537. Min Act: -0.0003

Data Index: 39363 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0531. Min Act: -0.0003

Data Index: 793306 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0415. Min Act: -0.0002

Data Index: 433934 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0405. Min Act: -0.0002

Data Index: 945103 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0393. Min Act: -0.0002

Data Index: 359083 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1078218 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1476406 (Python Code)

Max Activating Token Index: 353

Text #7

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0348. Min Act: -0.0003

Data Index: 519699 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0337. Min Act: -0.0003

Data Index: 414499 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1487266 (Python Code)

Max Activating Token Index: 308

Text #10

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0326. Min Act: -0.0003

Data Index: 603154 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0304. Min Act: -0.0003

Data Index: 758716 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0288. Min Act: -0.0003

Data Index: 525425 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1375181 (Python Code)

Max Activating Token Index: 232

Text #14

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1446854 (Python Code)

Max Activating Token Index: 460

Text #15

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0296. Min Act: -0.0002

Data Index: 899889 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0293. Min Act: -0.0003

Data Index: 27391 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1384281 (Python Code)

Max Activating Token Index: 377

Text #18

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1566953 (Python Code)

Max Activating Token Index: 349

Text #19

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1377381 (Python Code)

Max Activating Token Index: 445