Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3042 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1924. Min Act: -0.0001

Data Index: 142735 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1599. Min Act: -0.0000

Data Index: 21929 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1530. Min Act: -0.0001

Data Index: 135361 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1429. Min Act: -0.0000

Data Index: 955219 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1468. Min Act: -0.0001

Data Index: 42462 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1453. Min Act: -0.0000

Data Index: 114242 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1562. Min Act: -0.0000

Data Index: 707695 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1047982 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1419. Min Act: -0.0000

Data Index: 218628 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1397. Min Act: -0.0001

Data Index: 857095 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1340. Min Act: -0.0000

Data Index: 455580 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1334. Min Act: -0.0000

Data Index: 858730 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1298. Min Act: -0.0001

Data Index: 69553 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1226151 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1234. Min Act: -0.0000

Data Index: 830622 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1198812 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1430. Min Act: -0.0000

Data Index: 149431 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1282. Min Act: -0.0001

Data Index: 606416 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1227. Min Act: -0.0000

Data Index: 784196 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.1924. Min Range: -0.1924

Max Act: 0.1269. Min Act: -0.0001

Data Index: 41165 (C4 (Web Text))

Max Activating Token Index: 326