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

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

Neuron 2958 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.6229. Min Act: -0.0000

Data Index: 859712 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.4550. Min Act: -0.0000

Data Index: 520624 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.3870. Min Act: -0.0000

Data Index: 108894 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.3253. Min Act: -0.0000

Data Index: 396930 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2282. Min Act: -0.0000

Data Index: 34747 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2677. Min Act: -0.0000

Data Index: 439558 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2685. Min Act: -0.0000

Data Index: 827679 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2222. Min Act: -0.0000

Data Index: 1338771 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2546. Min Act: -0.0000

Data Index: 56581 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2064. Min Act: -0.0000

Data Index: 220388 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1986. Min Act: -0.0000

Data Index: 1238788 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1969. Min Act: -0.0000

Data Index: 147637 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1205. Min Act: -0.0000

Data Index: 1130588 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1729. Min Act: -0.0000

Data Index: 828149 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1219503 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.0756. Min Act: -0.0000

Data Index: 37100 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2195. Min Act: -0.0000

Data Index: 342442 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2198. Min Act: -0.0000

Data Index: 3959 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.2011. Min Act: -0.0000

Data Index: 272467 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 1.6229. Min Range: -1.6229

Max Act: 1.1227. Min Act: -0.0000

Data Index: 878839 (C4 (Web Text))

Max Activating Token Index: 641