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

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

Neuron 461 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0740. Min Act: 0.0001

Data Index: 194804 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0001

Data Index: 294431 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0679. Min Act: 0.0000

Data Index: 298007 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1194741 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1163015 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1230153 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0630. Min Act: -0.0002

Data Index: 313904 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0627. Min Act: 0.0001

Data Index: 564798 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0622. Min Act: -0.0001

Data Index: 929454 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0624. Min Act: -0.0002

Data Index: 891557 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0633. Min Act: -0.0002

Data Index: 261442 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0604. Min Act: -0.0000

Data Index: 271736 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0605. Min Act: -0.0002

Data Index: 859002 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0613. Min Act: -0.0001

Data Index: 508159 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0600. Min Act: -0.0002

Data Index: 444855 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0613. Min Act: 0.0001

Data Index: 1165288 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1085336 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0585. Min Act: -0.0002

Data Index: 747447 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1170594 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0599. Min Act: -0.0002

Data Index: 826176 (C4 (Web Text))

Max Activating Token Index: 534