Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 195 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.8653. Min Act: -0.0004

Data Index: 1324520 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6271. Min Act: -0.0004

Data Index: 1261285 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6693. Min Act: -0.0004

Data Index: 966305 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6124. Min Act: -0.0004

Data Index: 315976 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.6424. Min Act: -0.0004

Data Index: 1327730 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5609. Min Act: -0.0004

Data Index: 30706 (C4 (Web Text))

Max Activating Token Index: 626

Text #6

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5817. Min Act: -0.0004

Data Index: 149274 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5972. Min Act: -0.0004

Data Index: 905339 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5544. Min Act: -0.0004

Data Index: 465581 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5651. Min Act: -0.0004

Data Index: 1285965 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5623. Min Act: -0.0004

Data Index: 649333 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5322. Min Act: -0.0004

Data Index: 1080243 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.4902. Min Act: -0.0004

Data Index: 899384 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5353. Min Act: -0.0004

Data Index: 1032226 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5460. Min Act: -0.0004

Data Index: 69829 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5284. Min Act: -0.0004

Data Index: 154715 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5429. Min Act: -0.0004

Data Index: 937790 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5177. Min Act: -0.0004

Data Index: 536073 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.5114. Min Act: -0.0004

Data Index: 933443 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.8653. Min Range: -0.8653

Max Act: 0.4947. Min Act: -0.0004

Data Index: 1096264 (C4 (Web Text))

Max Activating Token Index: 947