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

Dataset: The Pile

Neuron 2833 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0766. Min Range: -1.0766

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1233358 (The Pile)

Max Activating Token Index: 782

Text #1

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1557464 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1762798 (The Pile)

Max Activating Token Index: 996

Text #3

Max Range: 1.0766. Min Range: -1.0766

Max Act: 1.0424. Min Act: -0.0000

Data Index: 792330 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9857. Min Act: -0.0000

Data Index: 624864 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9572. Min Act: -0.0000

Data Index: 750016 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8673. Min Act: -0.0001

Data Index: 146899 (The Pile)

Max Activating Token Index: 969

Text #7

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9711. Min Act: -0.0000

Data Index: 444352 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9041. Min Act: -0.0000

Data Index: 1461840 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1045925 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9097. Min Act: -0.0000

Data Index: 405810 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.9400. Min Act: -0.0000

Data Index: 315987 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1678497 (The Pile)

Max Activating Token Index: 715

Text #13

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8420. Min Act: -0.0001

Data Index: 1748263 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8626. Min Act: -0.0000

Data Index: 648529 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8224. Min Act: -0.0000

Data Index: 921594 (The Pile)

Max Activating Token Index: 801

Text #16

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1388917 (The Pile)

Max Activating Token Index: 497

Text #17

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.7692. Min Act: -0.0000

Data Index: 41579 (The Pile)

Max Activating Token Index: 478

Text #18

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1940992 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 1.0766. Min Range: -1.0766

Max Act: 0.8629. Min Act: -0.0000

Data Index: 456297 (The Pile)

Max Activating Token Index: 574