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

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

Neuron 481 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: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1557338 (Python Code)

Max Activating Token Index: 332

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0470. Min Act: -0.0002

Data Index: 753550 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0464. Min Act: -0.0002

Data Index: 828183 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1462842 (Python Code)

Max Activating Token Index: 694

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1653937 (Python Code)

Max Activating Token Index: 529

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0434. Min Act: -0.0002

Data Index: 115985 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0426. Min Act: -0.0002

Data Index: 356408 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0397. Min Act: -0.0002

Data Index: 781670 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0409. Min Act: -0.0002

Data Index: 219488 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0400. Min Act: -0.0002

Data Index: 276727 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0401. Min Act: -0.0002

Data Index: 772836 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1001323 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1325549 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0390. Min Act: -0.0002

Data Index: 20067 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1652738 (Python Code)

Max Activating Token Index: 527

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1573809 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0375. Min Act: -0.0002

Data Index: 674525 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0386. Min Act: -0.0002

Data Index: 1357200 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1546976 (Python Code)

Max Activating Token Index: 964

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1527494 (Python Code)

Max Activating Token Index: 381