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

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

Neuron 4699 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.9048. Min Act: -0.0000

Data Index: 300704 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.5977. Min Act: -0.0000

Data Index: 39392 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.6818. Min Act: -0.0000

Data Index: 1100956 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.5444. Min Act: -0.0000

Data Index: 1246132 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.5355. Min Act: -0.0000

Data Index: 508727 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.5119. Min Act: -0.0000

Data Index: 145409 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.5044. Min Act: -0.0000

Data Index: 1329464 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.4149. Min Act: -0.0000

Data Index: 470652 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.4822. Min Act: -0.0000

Data Index: 925824 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.4580. Min Act: -0.0000

Data Index: 828998 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.4404. Min Act: -0.0000

Data Index: 1071762 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.4383. Min Act: -0.0000

Data Index: 513017 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.4275. Min Act: -0.0000

Data Index: 433303 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.4161. Min Act: -0.0000

Data Index: 50144 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.4961. Min Act: -0.0000

Data Index: 658239 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.4016. Min Act: -0.0000

Data Index: 385823 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.4772. Min Act: -0.0000

Data Index: 462345 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.3521. Min Act: -0.0001

Data Index: 825069 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.2237. Min Act: -0.0000

Data Index: 824559 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 1.9048. Min Range: -1.9048

Max Act: 1.4205. Min Act: -0.0000

Data Index: 288873 (C4 (Web Text))

Max Activating Token Index: 276