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

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

Neuron 1476 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: 0.0644. Min Range: -0.0644

Max Act: 0.0644. Min Act: -0.0003

Data Index: 890586 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0621. Min Act: -0.0003

Data Index: 75499 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0617. Min Act: -0.0003

Data Index: 686933 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1120797 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0582. Min Act: -0.0003

Data Index: 400799 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0615. Min Act: -0.0002

Data Index: 635130 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0597. Min Act: -0.0003

Data Index: 296441 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1348759 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0584. Min Act: -0.0002

Data Index: 326542 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0592. Min Act: -0.0003

Data Index: 109146 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1003833 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0579. Min Act: -0.0004

Data Index: 84029 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1228861 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0566. Min Act: -0.0003

Data Index: 1129960 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0583. Min Act: -0.0003

Data Index: 216574 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0582. Min Act: -0.0003

Data Index: 277796 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0560. Min Act: -0.0003

Data Index: 895612 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0573. Min Act: -0.0003

Data Index: 704340 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0561. Min Act: -0.0003

Data Index: 290120 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0576. Min Act: -0.0004

Data Index: 616387 (C4 (Web Text))

Max Activating Token Index: 775