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

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

Neuron 928 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: 12.0544. Min Range: -12.0544

Max Act: 12.0544. Min Act: -0.0001

Data Index: 1350917 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 12.0544. Min Range: -12.0544

Max Act: 10.5107. Min Act: -0.0001

Data Index: 1165640 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 12.0544. Min Range: -12.0544

Max Act: 10.8763. Min Act: -0.0001

Data Index: 1276793 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 12.0544. Min Range: -12.0544

Max Act: 10.2399. Min Act: -0.0001

Data Index: 268513 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 12.0544. Min Range: -12.0544

Max Act: 10.7733. Min Act: -0.0001

Data Index: 67399 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 12.0544. Min Range: -12.0544

Max Act: 9.1227. Min Act: -0.0001

Data Index: 712688 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.9279. Min Act: -0.0001

Data Index: 859102 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.9704. Min Act: -0.0001

Data Index: 903585 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 12.0544. Min Range: -12.0544

Max Act: 9.3300. Min Act: -0.0001

Data Index: 302683 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 12.0544. Min Range: -12.0544

Max Act: 9.0099. Min Act: -0.0001

Data Index: 182979 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.8602. Min Act: -0.0001

Data Index: 658888 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.8212. Min Act: -0.0001

Data Index: 669089 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.3901. Min Act: -0.0001

Data Index: 38480 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.3363. Min Act: -0.0001

Data Index: 54241 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.2695. Min Act: -0.0001

Data Index: 385349 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.3601. Min Act: -0.0001

Data Index: 1055736 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.1574. Min Act: -0.0001

Data Index: 577745 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.1294. Min Act: -0.0001

Data Index: 657258 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.1589. Min Act: -0.0001

Data Index: 1086987 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 12.0544. Min Range: -12.0544

Max Act: 8.1097. Min Act: -0.0001

Data Index: 758049 (C4 (Web Text))

Max Activating Token Index: 45