Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 310 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.8607. Min Act: -0.0000

Data Index: 209396 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.7421. Min Act: -0.0001

Data Index: 784833 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.6341. Min Act: -0.0001

Data Index: 414941 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.6283. Min Act: -0.0001

Data Index: 1284371 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.6005. Min Act: -0.0000

Data Index: 181357 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.6010. Min Act: -0.0001

Data Index: 289914 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.5584. Min Act: -0.0001

Data Index: 867746 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.4828. Min Act: -0.0000

Data Index: 332848 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.4669. Min Act: -0.0001

Data Index: 568287 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.4278. Min Act: -0.0001

Data Index: 853923 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.4696. Min Act: -0.0000

Data Index: 145097 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.5460. Min Act: -0.0000

Data Index: 216530 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.4587. Min Act: -0.0000

Data Index: 636006 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1207223 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.5163. Min Act: -0.0001

Data Index: 551092 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.4310. Min Act: -0.0001

Data Index: 758310 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.4248. Min Act: -0.0001

Data Index: 449806 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.5113. Min Act: -0.0001

Data Index: 74891 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.6080. Min Act: -0.0001

Data Index: 1138487 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.8607. Min Range: -1.8607

Max Act: 1.3422. Min Act: -0.0000

Data Index: 315863 (C4 (Web Text))

Max Activating Token Index: 796