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

Dataset: The Pile

Neuron 871 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0933. Min Act: -0.0000

Data Index: 245994 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0780. Min Act: -0.0000

Data Index: 985786 (The Pile)

Max Activating Token Index: 744

Text #2

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0706. Min Act: -0.0000

Data Index: 927387 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0689. Min Act: -0.0000

Data Index: 30593 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1348774 (The Pile)

Max Activating Token Index: 812

Text #5

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1777597 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0634. Min Act: -0.0000

Data Index: 765925 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1490235 (The Pile)

Max Activating Token Index: 923

Text #8

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0606. Min Act: -0.0000

Data Index: 500329 (The Pile)

Max Activating Token Index: 875

Text #9

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1442343 (The Pile)

Max Activating Token Index: 806

Text #10

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0624. Min Act: -0.0000

Data Index: 828469 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1999870 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1394874 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1774110 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1760853 (The Pile)

Max Activating Token Index: 941

Text #15

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1421019 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0542. Min Act: -0.0000

Data Index: 165953 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1023344 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0557. Min Act: -0.0000

Data Index: 484834 (The Pile)

Max Activating Token Index: 963

Text #19

Max Range: 0.0933. Min Range: -0.0933

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1075881 (The Pile)

Max Activating Token Index: 928