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

Dataset: The Pile

Neuron 2437 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5873. Min Range: -3.5873

Max Act: 3.5873. Min Act: -0.0000

Data Index: 1646979 (The Pile)

Max Activating Token Index: 663

Text #1

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.9172. Min Act: -0.0000

Data Index: 417173 (The Pile)

Max Activating Token Index: 963

Text #2

Max Range: 3.5873. Min Range: -3.5873

Max Act: 2.1960. Min Act: -0.0000

Data Index: 1225428 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 3.5873. Min Range: -3.5873

Max Act: 1.6252. Min Act: -0.0000

Data Index: 1381521 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 3.5873. Min Range: -3.5873

Max Act: 1.2984. Min Act: -0.0000

Data Index: 106960 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 3.5873. Min Range: -3.5873

Max Act: 1.2888. Min Act: -0.0000

Data Index: 570456 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 3.5873. Min Range: -3.5873

Max Act: 1.3551. Min Act: -0.0000

Data Index: 141227 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 3.5873. Min Range: -3.5873

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1707941 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 3.5873. Min Range: -3.5873

Max Act: 0.8760. Min Act: -0.0000

Data Index: 500590 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 3.5873. Min Range: -3.5873

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1225931 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 3.5873. Min Range: -3.5873

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1241983 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 3.5873. Min Range: -3.5873

Max Act: 1.0264. Min Act: -0.0000

Data Index: 750049 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 3.5873. Min Range: -3.5873

Max Act: 0.8539. Min Act: -0.0000

Data Index: 809638 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 3.5873. Min Range: -3.5873

Max Act: 0.9346. Min Act: -0.0000

Data Index: 935251 (The Pile)

Max Activating Token Index: 485

Text #14

Max Range: 3.5873. Min Range: -3.5873

Max Act: 0.8628. Min Act: -0.0000

Data Index: 600885 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 3.5873. Min Range: -3.5873

Max Act: 0.8601. Min Act: -0.0000

Data Index: 153758 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 3.5873. Min Range: -3.5873

Max Act: 0.7371. Min Act: -0.0000

Data Index: 504307 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 3.5873. Min Range: -3.5873

Max Act: 0.7921. Min Act: -0.0000

Data Index: 540590 (The Pile)

Max Activating Token Index: 165

Text #18

Max Range: 3.5873. Min Range: -3.5873

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1208240 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 3.5873. Min Range: -3.5873

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1150637 (The Pile)

Max Activating Token Index: 123