Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2421 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1399371 (The Pile)

Max Activating Token Index: 242

Text #1

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.8695. Min Act: -0.0000

Data Index: 358694 (The Pile)

Max Activating Token Index: 765

Text #2

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.8595. Min Act: -0.0000

Data Index: 352132 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1052333 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1680843 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7772. Min Act: -0.0000

Data Index: 762838 (The Pile)

Max Activating Token Index: 354

Text #6

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.8498. Min Act: -0.0000

Data Index: 44897 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7755. Min Act: -0.0000

Data Index: 981526 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7560. Min Act: -0.0000

Data Index: 652841 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7749. Min Act: -0.0000

Data Index: 770159 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7779. Min Act: -0.0000

Data Index: 213645 (The Pile)

Max Activating Token Index: 761

Text #11

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7609. Min Act: -0.0000

Data Index: 13207 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1984731 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7240. Min Act: -0.0000

Data Index: 35320 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7423. Min Act: -0.0000

Data Index: 404374 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7381. Min Act: -0.0000

Data Index: 594009 (The Pile)

Max Activating Token Index: 669

Text #16

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1257655 (The Pile)

Max Activating Token Index: 198

Text #17

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1471653 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7425. Min Act: -0.0000

Data Index: 234500 (The Pile)

Max Activating Token Index: 886

Text #19

Max Range: 0.9663. Min Range: -0.9663

Max Act: 0.7136. Min Act: -0.0000

Data Index: 240697 (The Pile)

Max Activating Token Index: 998