Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1582 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0801. Min Act: -0.0003

Data Index: 40212 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0735. Min Act: -0.0004

Data Index: 312391 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0704. Min Act: -0.0003

Data Index: 1287208 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1030082 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0687. Min Act: -0.0002

Data Index: 52933 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0645. Min Act: -0.0003

Data Index: 202834 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1281578 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0630. Min Act: -0.0003

Data Index: 574856 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0639. Min Act: -0.0004

Data Index: 199582 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0630. Min Act: -0.0003

Data Index: 48790 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0614. Min Act: -0.0003

Data Index: 1327121 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0621. Min Act: -0.0002

Data Index: 907834 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1192978 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0606. Min Act: -0.0003

Data Index: 219149 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0621. Min Act: -0.0003

Data Index: 850339 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0609. Min Act: -0.0002

Data Index: 827296 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1246715 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0602. Min Act: -0.0003

Data Index: 568118 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0622. Min Act: -0.0003

Data Index: 1281930 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0613. Min Act: -0.0004

Data Index: 654299 (C4 (Web Text))

Max Activating Token Index: 622