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

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

Neuron 1678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3272. Min Range: -2.3272

Max Act: 2.2658. Min Act: -0.0000

Data Index: 49942 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 2.3272. Min Range: -2.3272

Max Act: 2.0606. Min Act: -0.0000

Data Index: 565591 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 2.3272. Min Range: -2.3272

Max Act: 2.1606. Min Act: -0.0000

Data Index: 1108462 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 2.3272. Min Range: -2.3272

Max Act: 2.3272. Min Act: -0.0000

Data Index: 737846 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 2.3272. Min Range: -2.3272

Max Act: 2.0867. Min Act: -0.0000

Data Index: 1126973 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 2.3272. Min Range: -2.3272

Max Act: 2.1666. Min Act: -0.0000

Data Index: 1198628 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 2.3272. Min Range: -2.3272

Max Act: 2.1480. Min Act: -0.0000

Data Index: 659435 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.9886. Min Act: -0.0000

Data Index: 330045 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.9772. Min Act: -0.0000

Data Index: 1173518 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.6889. Min Act: -0.0000

Data Index: 1310499 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.8852. Min Act: -0.0000

Data Index: 499105 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.9321. Min Act: -0.0000

Data Index: 259919 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.8032. Min Act: -0.0000

Data Index: 981648 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.8185. Min Act: -0.0000

Data Index: 671613 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.8544. Min Act: -0.0000

Data Index: 505384 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.6863. Min Act: -0.0000

Data Index: 833395 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.6343. Min Act: -0.0000

Data Index: 850010 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.7194. Min Act: -0.0000

Data Index: 826327 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1023526 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 2.3272. Min Range: -2.3272

Max Act: 1.7618. Min Act: -0.0000

Data Index: 422100 (C4 (Web Text))

Max Activating Token Index: 941