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

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

Neuron 1254 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: 0.1022. Min Range: -0.1022

Max Act: 0.1022. Min Act: -0.0005

Data Index: 209755 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0834. Min Act: -0.0005

Data Index: 376759 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0807. Min Act: -0.0005

Data Index: 481759 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0824. Min Act: -0.0005

Data Index: 845583 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0784. Min Act: -0.0005

Data Index: 783391 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0770. Min Act: -0.0005

Data Index: 755950 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0799. Min Act: -0.0005

Data Index: 413316 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0792. Min Act: -0.0005

Data Index: 604367 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0764. Min Act: -0.0005

Data Index: 1278178 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0777. Min Act: -0.0005

Data Index: 811233 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0798. Min Act: -0.0005

Data Index: 616839 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0766. Min Act: -0.0005

Data Index: 1081750 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0746. Min Act: -0.0005

Data Index: 1159834 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0781. Min Act: -0.0005

Data Index: 740769 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0727. Min Act: -0.0005

Data Index: 1339242 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0738. Min Act: -0.0005

Data Index: 350597 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0726. Min Act: -0.0005

Data Index: 1206196 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0648. Min Act: -0.0005

Data Index: 1218230 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0698. Min Act: -0.0005

Data Index: 733123 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0725. Min Act: -0.0005

Data Index: 249341 (C4 (Web Text))

Max Activating Token Index: 561