Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3496 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1928. Min Act: -0.0001

Data Index: 1151615 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1775. Min Act: -0.0002

Data Index: 330309 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1828. Min Act: -0.0001

Data Index: 391892 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1886. Min Act: -0.0001

Data Index: 546731 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1816. Min Act: -0.0002

Data Index: 409659 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1821. Min Act: -0.0001

Data Index: 157316 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1757. Min Act: -0.0002

Data Index: 662874 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1756. Min Act: -0.0001

Data Index: 532242 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1818. Min Act: -0.0002

Data Index: 45263 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1773. Min Act: -0.0002

Data Index: 365540 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1573. Min Act: -0.0002

Data Index: 244412 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1761. Min Act: -0.0002

Data Index: 660763 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1666. Min Act: -0.0002

Data Index: 69469 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1776. Min Act: -0.0001

Data Index: 895387 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1651. Min Act: -0.0001

Data Index: 621619 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1649. Min Act: -0.0001

Data Index: 646627 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1410. Min Act: -0.0002

Data Index: 1346874 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1666. Min Act: -0.0001

Data Index: 149674 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1683. Min Act: -0.0002

Data Index: 384492 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1548. Min Act: -0.0001

Data Index: 230816 (C4 (Web Text))

Max Activating Token Index: 656