Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4226 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.4392. Min Act: -0.0000

Data Index: 1418748 (Python Code)

Max Activating Token Index: 983

Text #1

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.3963. Min Act: 0.0000

Data Index: 589407 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.4602. Min Act: -0.0000

Data Index: 570847 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.4170. Min Act: -0.0000

Data Index: 827781 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.3777. Min Act: 0.0000

Data Index: 1212879 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.3460. Min Act: -0.0000

Data Index: 694903 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.3344. Min Act: 0.0000

Data Index: 399222 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.2099. Min Act: 0.0000

Data Index: 768831 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.2506. Min Act: -0.0000

Data Index: 611194 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.2582. Min Act: -0.0000

Data Index: 299010 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.2246. Min Act: 0.0000

Data Index: 1313496 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.2318. Min Act: -0.0000

Data Index: 559502 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.0642. Min Act: 0.0000

Data Index: 1450187 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1427381 (Python Code)

Max Activating Token Index: 344

Text #14

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1045399 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.0326. Min Act: -0.0000

Data Index: 1653118 (Python Code)

Max Activating Token Index: 389

Text #16

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.0233. Min Act: -0.0000

Data Index: 717914 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.4602. Min Range: -1.4602

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1569102 (Python Code)

Max Activating Token Index: 471

Text #18

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.0810. Min Act: -0.0000

Data Index: 124307 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 1.4602. Min Range: -1.4602

Max Act: 1.0252. Min Act: 0.0000

Data Index: 620566 (C4 (Web Text))

Max Activating Token Index: 977