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

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

Neuron 2724 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: 2.8353. Min Range: -2.8353

Max Act: 2.8353. Min Act: -0.0001

Data Index: 977500 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.5910. Min Act: -0.0000

Data Index: 387972 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.4339. Min Act: -0.0000

Data Index: 965648 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.1255. Min Act: -0.0000

Data Index: 154624 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.2965. Min Act: -0.0000

Data Index: 804733 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.1353. Min Act: -0.0000

Data Index: 292381 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.3611. Min Act: -0.0000

Data Index: 1251593 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.0271. Min Act: -0.0000

Data Index: 45724 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.3534. Min Act: -0.0000

Data Index: 1048779 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.2447. Min Act: -0.0000

Data Index: 282829 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.3397. Min Act: -0.0001

Data Index: 955147 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.2265. Min Act: -0.0000

Data Index: 1130986 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.1055. Min Act: -0.0000

Data Index: 544942 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.0958. Min Act: -0.0001

Data Index: 237363 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.0901. Min Act: -0.0000

Data Index: 1308828 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.2943. Min Act: -0.0001

Data Index: 211205 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 2.8353. Min Range: -2.8353

Max Act: 1.9701. Min Act: -0.0000

Data Index: 388185 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.4224. Min Act: -0.0000

Data Index: 780990 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.1622. Min Act: -0.0000

Data Index: 225520 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 2.8353. Min Range: -2.8353

Max Act: 2.1571. Min Act: -0.0000

Data Index: 1151165 (C4 (Web Text))

Max Activating Token Index: 520