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

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

Neuron 1319 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.8382. Min Act: -0.0000

Data Index: 884163 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.8318. Min Act: -0.0000

Data Index: 20783 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7618. Min Act: -0.0000

Data Index: 868242 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7954. Min Act: -0.0000

Data Index: 584634 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7511. Min Act: -0.0000

Data Index: 538333 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7042. Min Act: -0.0000

Data Index: 277606 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7309. Min Act: -0.0000

Data Index: 941713 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1145670 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.7025. Min Act: -0.0000

Data Index: 280394 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1071976 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6589. Min Act: -0.0000

Data Index: 803828 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6869. Min Act: -0.0000

Data Index: 150363 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6770. Min Act: -0.0000

Data Index: 280057 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6584. Min Act: -0.0000

Data Index: 712217 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6370. Min Act: -0.0000

Data Index: 94510 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6122. Min Act: -0.0000

Data Index: 333395 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6696. Min Act: -0.0000

Data Index: 664512 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1087797 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6242. Min Act: -0.0000

Data Index: 680691 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.8382. Min Range: -0.8382

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1321827 (C4 (Web Text))

Max Activating Token Index: 949