Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1832 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2349. Min Range: -1.2349

Max Act: 1.2349. Min Act: -0.0000

Data Index: 487932 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 1.2349. Min Range: -1.2349

Max Act: 1.2253. Min Act: -0.0000

Data Index: 584440 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.2349. Min Range: -1.2349

Max Act: 1.1750. Min Act: -0.0000

Data Index: 885845 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.2349. Min Range: -1.2349

Max Act: 1.1436. Min Act: -0.0000

Data Index: 725733 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 1.2349. Min Range: -1.2349

Max Act: 1.1382. Min Act: -0.0000

Data Index: 867157 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 1.2349. Min Range: -1.2349

Max Act: 1.1247. Min Act: -0.0000

Data Index: 260123 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.2349. Min Range: -1.2349

Max Act: 1.0281. Min Act: -0.0000

Data Index: 51960 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 1.2349. Min Range: -1.2349

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1208629 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.9820. Min Act: -0.0000

Data Index: 23215 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.9733. Min Act: -0.0000

Data Index: 995463 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.9511. Min Act: -0.0000

Data Index: 1307707 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1180896 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.9285. Min Act: -0.0000

Data Index: 846547 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.9217. Min Act: -0.0000

Data Index: 556165 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.9110. Min Act: -0.0000

Data Index: 719778 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.9611. Min Act: -0.0000

Data Index: 71293 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.8882. Min Act: -0.0000

Data Index: 941103 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.8777. Min Act: -0.0000

Data Index: 23077 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.8915. Min Act: -0.0000

Data Index: 141699 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 1.2349. Min Range: -1.2349

Max Act: 0.8914. Min Act: -0.0000

Data Index: 70187 (C4 (Web Text))

Max Activating Token Index: 310