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

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

Neuron 2877 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: 0.9570. Min Range: -0.9570

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1055876 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.7401. Min Act: -0.0000

Data Index: 756102 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1132832 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.7221. Min Act: -0.0001

Data Index: 926642 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6865. Min Act: -0.0000

Data Index: 658175 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1039596 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.7240. Min Act: -0.0001

Data Index: 619423 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6733. Min Act: -0.0000

Data Index: 542126 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6517. Min Act: -0.0001

Data Index: 876947 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6395. Min Act: -0.0001

Data Index: 359012 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1263213 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1166827 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6764. Min Act: -0.0000

Data Index: 951356 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.7194. Min Act: -0.0000

Data Index: 941661 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6515. Min Act: -0.0000

Data Index: 569303 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6281. Min Act: -0.0001

Data Index: 1088555 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6534. Min Act: -0.0000

Data Index: 781944 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6310. Min Act: -0.0000

Data Index: 829427 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6247. Min Act: -0.0000

Data Index: 667643 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.9570. Min Range: -0.9570

Max Act: 0.6241. Min Act: -0.0000

Data Index: 701908 (C4 (Web Text))

Max Activating Token Index: 484