Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1772 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0779. Min Act: -0.0005

Data Index: 1274925 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0695. Min Act: -0.0005

Data Index: 1203521 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0661. Min Act: -0.0005

Data Index: 1312895 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0680. Min Act: -0.0005

Data Index: 485935 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0657. Min Act: -0.0005

Data Index: 607129 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0640. Min Act: -0.0005

Data Index: 1003872 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0620. Min Act: -0.0005

Data Index: 755196 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0614. Min Act: -0.0005

Data Index: 1189434 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0609. Min Act: -0.0005

Data Index: 943609 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0598. Min Act: -0.0005

Data Index: 1128973 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0607. Min Act: -0.0005

Data Index: 991553 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0597. Min Act: -0.0005

Data Index: 609580 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0590. Min Act: -0.0005

Data Index: 1259055 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0600. Min Act: -0.0005

Data Index: 168743 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0597. Min Act: -0.0005

Data Index: 1086916 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0606. Min Act: -0.0005

Data Index: 289498 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0595. Min Act: -0.0005

Data Index: 708584 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0592. Min Act: -0.0005

Data Index: 150029 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0587. Min Act: -0.0005

Data Index: 1086307 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0573. Min Act: -0.0005

Data Index: 1336453 (C4 (Web Text))

Max Activating Token Index: 38