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

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

Neuron 4722 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.2739. Min Act: -0.0000

Data Index: 267395 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.4257. Min Act: -0.0000

Data Index: 304443 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.3573. Min Act: -0.0000

Data Index: 696612 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.3360. Min Act: -0.0001

Data Index: 913634 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.9497. Min Act: -0.0000

Data Index: 1117192 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.9632. Min Act: -0.0000

Data Index: 810617 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.3449. Min Act: -0.0000

Data Index: 820218 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.7686. Min Act: -0.0000

Data Index: 547034 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.7834. Min Act: -0.0000

Data Index: 669023 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.0207. Min Act: -0.0000

Data Index: 781155 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 3.4257. Min Range: -3.4257

Max Act: 3.0066. Min Act: -0.0000

Data Index: 590132 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.8553. Min Act: -0.0000

Data Index: 608373 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.8428. Min Act: -0.0000

Data Index: 55106 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.9649. Min Act: -0.0000

Data Index: 430032 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.9678. Min Act: -0.0000

Data Index: 496193 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.9659. Min Act: -0.0000

Data Index: 1256397 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.8566. Min Act: -0.0000

Data Index: 348558 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.8377. Min Act: -0.0000

Data Index: 777778 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.8347. Min Act: -0.0000

Data Index: 973104 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 3.4257. Min Range: -3.4257

Max Act: 2.9306. Min Act: -0.0000

Data Index: 1179887 (C4 (Web Text))

Max Activating Token Index: 950