Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2802 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1453032 (The Pile)

Max Activating Token Index: 393

Text #1

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0937. Min Act: -0.0000

Data Index: 707566 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0803. Min Act: -0.0000

Data Index: 168587 (The Pile)

Max Activating Token Index: 530

Text #3

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1273040 (The Pile)

Max Activating Token Index: 886

Text #4

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0807. Min Act: -0.0000

Data Index: 787612 (The Pile)

Max Activating Token Index: 718

Text #5

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0792. Min Act: -0.0000

Data Index: 297971 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1447618 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1444577 (The Pile)

Max Activating Token Index: 543

Text #8

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0816. Min Act: -0.0000

Data Index: 389496 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0805. Min Act: -0.0000

Data Index: 823931 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0743. Min Act: -0.0000

Data Index: 306805 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0768. Min Act: -0.0000

Data Index: 509018 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1738249 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0780. Min Act: -0.0000

Data Index: 787132 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0714. Min Act: -0.0000

Data Index: 8592 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1112276 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0754. Min Act: -0.0000

Data Index: 301238 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0739. Min Act: -0.0000

Data Index: 908865 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0672. Min Act: -0.0000

Data Index: 684162 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0767. Min Act: -0.0000

Data Index: 317643 (The Pile)

Max Activating Token Index: 823