Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1123 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2352. Min Range: -1.2352

Max Act: 1.2232. Min Act: -0.0000

Data Index: 1340110 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.2352. Min Range: -1.2352

Max Act: 1.2352. Min Act: -0.0000

Data Index: 579166 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.2352. Min Range: -1.2352

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1124129 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 1.2352. Min Range: -1.2352

Max Act: 1.1775. Min Act: -0.0000

Data Index: 931717 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.2352. Min Range: -1.2352

Max Act: 1.1543. Min Act: 0.0000

Data Index: 1240631 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9967. Min Act: -0.0000

Data Index: 839560 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 1.2352. Min Range: -1.2352

Max Act: 1.0145. Min Act: -0.0001

Data Index: 258249 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9809. Min Act: -0.0000

Data Index: 677008 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9863. Min Act: -0.0000

Data Index: 702801 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.9611. Min Act: -0.0000

Data Index: 190146 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8898. Min Act: -0.0000

Data Index: 411390 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8595. Min Act: -0.0001

Data Index: 1206369 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8546. Min Act: -0.0000

Data Index: 1231409 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8343. Min Act: -0.0000

Data Index: 563697 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.7999. Min Act: -0.0000

Data Index: 547671 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8069. Min Act: -0.0000

Data Index: 891315 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.7782. Min Act: -0.0000

Data Index: 54562 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8225. Min Act: -0.0001

Data Index: 918879 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.8010. Min Act: -0.0000

Data Index: 132399 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 1.2352. Min Range: -1.2352

Max Act: 0.7013. Min Act: -0.0000

Data Index: 145667 (C4 (Web Text))

Max Activating Token Index: 664