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

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

Neuron 3630 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1659. Min Act: -0.0000

Data Index: 1071631 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.0346. Min Act: -0.0000

Data Index: 760359 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9690. Min Act: -0.0000

Data Index: 144483 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.0235. Min Act: -0.0000

Data Index: 1311017 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9754. Min Act: -0.0000

Data Index: 870904 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8449. Min Act: -0.0000

Data Index: 203394 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.9377. Min Act: -0.0000

Data Index: 553456 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8996. Min Act: -0.0000

Data Index: 533925 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1185887 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8232. Min Act: -0.0000

Data Index: 946048 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8465. Min Act: -0.0000

Data Index: 236697 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8910. Min Act: -0.0001

Data Index: 339409 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8459. Min Act: -0.0000

Data Index: 835985 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8706. Min Act: -0.0001

Data Index: 513880 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8303. Min Act: -0.0000

Data Index: 593264 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8899. Min Act: -0.0000

Data Index: 426481 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1125517 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8201. Min Act: -0.0000

Data Index: 380759 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8203. Min Act: -0.0000

Data Index: 293874 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 1.1659. Min Range: -1.1659

Max Act: 0.8206. Min Act: -0.0000

Data Index: 957834 (C4 (Web Text))

Max Activating Token Index: 934