Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1181 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1699. Min Act: -0.0001

Data Index: 288360 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1362437 (Python Code)

Max Activating Token Index: 613

Text #2

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1315. Min Act: -0.0001

Data Index: 676633 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1731. Min Act: -0.0001

Data Index: 51022 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1611. Min Act: -0.0001

Data Index: 927534 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1674. Min Act: -0.0001

Data Index: 639663 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1503. Min Act: -0.0001

Data Index: 1070172 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1067344 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1640. Min Act: -0.0001

Data Index: 857370 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1586. Min Act: -0.0001

Data Index: 405895 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1002510 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1655. Min Act: -0.0001

Data Index: 635971 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1491. Min Act: -0.0001

Data Index: 532507 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1497. Min Act: -0.0001

Data Index: 500574 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1499. Min Act: -0.0001

Data Index: 1390829 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1655989 (Python Code)

Max Activating Token Index: 412

Text #16

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1362. Min Act: -0.0001

Data Index: 80512 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1213907 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1406. Min Act: -0.0001

Data Index: 967400 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1418. Min Act: -0.0001

Data Index: 277001 (C4 (Web Text))

Max Activating Token Index: 364