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

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

Neuron 444 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: 0.0900. Min Range: -0.0900

Max Act: 0.0900. Min Act: -0.0004

Data Index: 1206558 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0866. Min Act: -0.0004

Data Index: 702852 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0798. Min Act: -0.0004

Data Index: 77642 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0829. Min Act: -0.0004

Data Index: 557664 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0806. Min Act: -0.0004

Data Index: 232444 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0804. Min Act: -0.0004

Data Index: 165185 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0801. Min Act: -0.0004

Data Index: 608267 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0789. Min Act: -0.0004

Data Index: 1019057 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0754. Min Act: -0.0004

Data Index: 554547 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0776. Min Act: -0.0004

Data Index: 1148249 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0800. Min Act: -0.0004

Data Index: 427399 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0773. Min Act: -0.0004

Data Index: 1324512 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0729. Min Act: -0.0004

Data Index: 190373 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0751. Min Act: -0.0004

Data Index: 1029855 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0749. Min Act: -0.0004

Data Index: 898699 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0744. Min Act: -0.0004

Data Index: 1302925 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0681. Min Act: -0.0004

Data Index: 653666 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0738. Min Act: -0.0004

Data Index: 93994 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0734. Min Act: -0.0004

Data Index: 1146289 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0733. Min Act: -0.0004

Data Index: 479119 (C4 (Web Text))

Max Activating Token Index: 762