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

Dataset: The Pile

Neuron 1427 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1312470 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0817. Min Act: -0.0000

Data Index: 20280 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1565048 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1718503 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0778. Min Act: -0.0000

Data Index: 676008 (The Pile)

Max Activating Token Index: 919

Text #5

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1011985 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1336640 (The Pile)

Max Activating Token Index: 744

Text #7

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0770. Min Act: 0.0000

Data Index: 605588 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0763. Min Act: -0.0000

Data Index: 454501 (The Pile)

Max Activating Token Index: 977

Text #9

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0762. Min Act: -0.0000

Data Index: 894331 (The Pile)

Max Activating Token Index: 888

Text #10

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0763. Min Act: 0.0000

Data Index: 306504 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1192322 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1551563 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0749. Min Act: -0.0000

Data Index: 844243 (The Pile)

Max Activating Token Index: 942

Text #14

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1894289 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0745. Min Act: -0.0000

Data Index: 1062151 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0743. Min Act: -0.0000

Data Index: 783602 (The Pile)

Max Activating Token Index: 705

Text #17

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1748376 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0734. Min Act: -0.0000

Data Index: 365001 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0730. Min Act: -0.0000

Data Index: 1660634 (The Pile)

Max Activating Token Index: 569