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

Dataset: The Pile

Neuron 4032 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: 1.3067. Min Range: -1.3067

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1707588 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1491. Min Act: -0.0000

Data Index: 305217 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1477337 (The Pile)

Max Activating Token Index: 85

Text #3

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0707. Min Act: -0.0000

Data Index: 91201 (The Pile)

Max Activating Token Index: 657

Text #4

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1117025 (The Pile)

Max Activating Token Index: 835

Text #5

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9903. Min Act: -0.0000

Data Index: 657191 (The Pile)

Max Activating Token Index: 1019

Text #6

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9392. Min Act: -0.0000

Data Index: 180613 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1715671 (The Pile)

Max Activating Token Index: 517

Text #8

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.8368. Min Act: -0.0000

Data Index: 1793458 (The Pile)

Max Activating Token Index: 518

Text #9

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1551708 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.8158. Min Act: -0.0000

Data Index: 235441 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.8791. Min Act: -0.0000

Data Index: 94379 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1721061 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1417576 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1549919 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1121830 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1723974 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.7708. Min Act: -0.0000

Data Index: 318975 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.7564. Min Act: -0.0000

Data Index: 426729 (The Pile)

Max Activating Token Index: 273

Text #19

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.6575. Min Act: -0.0000

Data Index: 745675 (The Pile)

Max Activating Token Index: 1002