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

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

Neuron 2351 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.9886. Min Act: -0.0000

Data Index: 838867 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.8194. Min Act: -0.0000

Data Index: 841733 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.8156. Min Act: -0.0000

Data Index: 154910 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.4311. Min Act: -0.0000

Data Index: 416566 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.3036. Min Act: 0.0000

Data Index: 1345690 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.3419. Min Act: -0.0000

Data Index: 69149 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.3364. Min Act: -0.0000

Data Index: 1127888 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.3302. Min Act: 0.0001

Data Index: 613732 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.2883. Min Act: -0.0000

Data Index: 1177291 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.3193. Min Act: -0.0000

Data Index: 66789 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.3075. Min Act: -0.0000

Data Index: 1069017 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.1279. Min Act: -0.0000

Data Index: 279845 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.3629. Min Act: -0.0000

Data Index: 62924 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.2766. Min Act: -0.0000

Data Index: 893719 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.2412. Min Act: -0.0000

Data Index: 1026268 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.1272. Min Act: -0.0000

Data Index: 677993 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1115322 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1171663 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.2312. Min Act: -0.0000

Data Index: 363765 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 1.9886. Min Range: -1.9886

Max Act: 1.2015. Min Act: -0.0000

Data Index: 99548 (C4 (Web Text))

Max Activating Token Index: 866