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

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

Neuron 4812 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1748. Min Act: -0.0001

Data Index: 872496 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8055. Min Act: -0.0001

Data Index: 548201 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8435. Min Act: -0.0001

Data Index: 1157542 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8317. Min Act: -0.0001

Data Index: 578418 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7876. Min Act: -0.0001

Data Index: 924995 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8087. Min Act: -0.0001

Data Index: 1313475 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7741. Min Act: -0.0001

Data Index: 635741 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7238. Min Act: -0.0001

Data Index: 1272000 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7665. Min Act: -0.0001

Data Index: 968832 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7351. Min Act: -0.0001

Data Index: 342672 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7172. Min Act: -0.0001

Data Index: 961467 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8421. Min Act: -0.0001

Data Index: 58509 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7174. Min Act: -0.0001

Data Index: 1326674 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7382. Min Act: -0.0001

Data Index: 1144390 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.6472. Min Act: -0.0001

Data Index: 315206 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7738. Min Act: -0.0001

Data Index: 172785 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7249. Min Act: -0.0001

Data Index: 252101 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7439. Min Act: -0.0001

Data Index: 558212 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.7341. Min Act: -0.0001

Data Index: 788075 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.6851. Min Act: -0.0001

Data Index: 949799 (C4 (Web Text))

Max Activating Token Index: 28