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

Dataset: The Pile

Neuron 2804 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: 0.2454. Min Range: -0.2454

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1090581 (The Pile)

Max Activating Token Index: 828

Text #1

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2382. Min Act: -0.0000

Data Index: 834229 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1372538 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2136. Min Act: -0.0000

Data Index: 220069 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.2048. Min Act: -0.0000

Data Index: 611438 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1864233 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1047814 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1239914 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1967. Min Act: -0.0000

Data Index: 783392 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1957. Min Act: -0.0000

Data Index: 546891 (The Pile)

Max Activating Token Index: 241

Text #10

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1437905 (The Pile)

Max Activating Token Index: 564

Text #11

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1748. Min Act: -0.0000

Data Index: 991726 (The Pile)

Max Activating Token Index: 1012

Text #12

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1540721 (The Pile)

Max Activating Token Index: 965

Text #13

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1382183 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1900. Min Act: -0.0000

Data Index: 322915 (The Pile)

Max Activating Token Index: 693

Text #15

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1569463 (The Pile)

Max Activating Token Index: 1018

Text #16

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1292912 (The Pile)

Max Activating Token Index: 363

Text #17

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1799. Min Act: -0.0000

Data Index: 773523 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1767780 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 0.2454. Min Range: -0.2454

Max Act: 0.1779. Min Act: -0.0000

Data Index: 748049 (The Pile)

Max Activating Token Index: 567