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

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

Neuron 3462 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: 5.6779. Min Range: -5.6779

Max Act: 5.6363. Min Act: -0.0000

Data Index: 164832 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 5.6779. Min Range: -5.6779

Max Act: 5.6779. Min Act: -0.0000

Data Index: 919681 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 5.6779. Min Range: -5.6779

Max Act: 5.5075. Min Act: -0.0000

Data Index: 157599 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 5.6779. Min Range: -5.6779

Max Act: 5.1686. Min Act: -0.0000

Data Index: 552233 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 5.6779. Min Range: -5.6779

Max Act: 5.2257. Min Act: -0.0000

Data Index: 125426 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.7119. Min Act: -0.0000

Data Index: 148847 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.9108. Min Act: -0.0001

Data Index: 291105 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.7606. Min Act: -0.0000

Data Index: 486328 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.8554. Min Act: -0.0000

Data Index: 282441 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.4532. Min Act: -0.0000

Data Index: 991423 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.6373. Min Act: -0.0000

Data Index: 1261995 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.7433. Min Act: -0.0000

Data Index: 704590 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.5748. Min Act: -0.0000

Data Index: 1161163 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.5229. Min Act: -0.0000

Data Index: 815497 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.8355. Min Act: -0.0000

Data Index: 260310 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.6495. Min Act: -0.0000

Data Index: 412582 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.4757. Min Act: -0.0000

Data Index: 742387 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.8122. Min Act: -0.0000

Data Index: 413082 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.2895. Min Act: -0.0000

Data Index: 977657 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 5.6779. Min Range: -5.6779

Max Act: 4.7993. Min Act: -0.0000

Data Index: 1243228 (C4 (Web Text))

Max Activating Token Index: 471