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

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

Neuron 4885 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.3254. Min Act: -0.0000

Data Index: 1059329 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.2984. Min Act: -0.0000

Data Index: 745783 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1925. Min Act: -0.0000

Data Index: 869330 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1861. Min Act: -0.0000

Data Index: 1130984 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1833. Min Act: -0.0000

Data Index: 775559 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1157390 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.2089. Min Act: -0.0000

Data Index: 217553 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1681. Min Act: -0.0000

Data Index: 661279 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1675. Min Act: -0.0000

Data Index: 262828 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.2290. Min Act: -0.0000

Data Index: 26630 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1508. Min Act: -0.0000

Data Index: 134302 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.2041. Min Act: -0.0000

Data Index: 1045318 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1618. Min Act: -0.0000

Data Index: 113953 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1156. Min Act: -0.0000

Data Index: 663202 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.0910. Min Act: -0.0000

Data Index: 650505 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1401. Min Act: -0.0000

Data Index: 593675 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1433. Min Act: -0.0000

Data Index: 524572 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1309. Min Act: -0.0000

Data Index: 706971 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.1308. Min Act: -0.0000

Data Index: 56204 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 1.3254. Min Range: -1.3254

Max Act: 1.0614. Min Act: -0.0000

Data Index: 422058 (C4 (Web Text))

Max Activating Token Index: 760