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

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

Neuron 4277 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1151. Min Range: -1.1151

Max Act: 1.0611. Min Act: -0.0001

Data Index: 1195851 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 1.1151. Min Range: -1.1151

Max Act: 1.0003. Min Act: -0.0000

Data Index: 628366 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 1.1151. Min Range: -1.1151

Max Act: 1.0669. Min Act: -0.0001

Data Index: 1326395 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1334146 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 1.1151. Min Range: -1.1151

Max Act: 1.0782. Min Act: -0.0001

Data Index: 98182 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9884. Min Act: -0.0001

Data Index: 398966 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9499. Min Act: -0.0001

Data Index: 367807 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.1151. Min Range: -1.1151

Max Act: 1.0576. Min Act: -0.0000

Data Index: 648133 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9238. Min Act: -0.0000

Data Index: 510751 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 1.1151. Min Range: -1.1151

Max Act: 1.1151. Min Act: -0.0001

Data Index: 1560348 (Python Code)

Max Activating Token Index: 699

Text #10

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9944. Min Act: -0.0001

Data Index: 722817 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 1.1151. Min Range: -1.1151

Max Act: 1.0015. Min Act: -0.0001

Data Index: 1493855 (Python Code)

Max Activating Token Index: 743

Text #12

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9951. Min Act: -0.0001

Data Index: 1652981 (Python Code)

Max Activating Token Index: 989

Text #13

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9379. Min Act: -0.0001

Data Index: 337976 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 1.1151. Min Range: -1.1151

Max Act: 1.0165. Min Act: -0.0001

Data Index: 898173 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9300. Min Act: -0.0001

Data Index: 1581919 (Python Code)

Max Activating Token Index: 970

Text #16

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9641. Min Act: -0.0001

Data Index: 1472426 (Python Code)

Max Activating Token Index: 548

Text #17

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9020. Min Act: -0.0000

Data Index: 333239 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9542. Min Act: -0.0001

Data Index: 1124775 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 1.1151. Min Range: -1.1151

Max Act: 0.9775. Min Act: -0.0001

Data Index: 451148 (C4 (Web Text))

Max Activating Token Index: 28