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

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

Neuron 604 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: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0003

Data Index: 75669 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1281280 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0661. Min Act: -0.0003

Data Index: 478325 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0661. Min Act: -0.0003

Data Index: 768921 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0636. Min Act: -0.0003

Data Index: 137276 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0654. Min Act: -0.0004

Data Index: 1131458 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0622. Min Act: -0.0002

Data Index: 259877 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1020471 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0646. Min Act: -0.0003

Data Index: 868804 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0637. Min Act: -0.0004

Data Index: 1121215 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1279227 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0612. Min Act: -0.0003

Data Index: 870533 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0603. Min Act: -0.0004

Data Index: 1056936 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1209284 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0594. Min Act: -0.0003

Data Index: 210116 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0581. Min Act: -0.0004

Data Index: 492742 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1322323 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0598. Min Act: -0.0004

Data Index: 766832 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0599. Min Act: -0.0003

Data Index: 616232 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0589. Min Act: -0.0003

Data Index: 996143 (C4 (Web Text))

Max Activating Token Index: 139