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

Dataset: The Pile

Neuron 127 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: 1.3813. Min Range: -1.3813

Max Act: 1.3813. Min Act: -0.0000

Data Index: 285821 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 1.3813. Min Range: -1.3813

Max Act: 1.0719. Min Act: -0.0000

Data Index: 1924821 (The Pile)

Max Activating Token Index: 727

Text #2

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.9718. Min Act: 0.0000

Data Index: 1914419 (The Pile)

Max Activating Token Index: 555

Text #3

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1890043 (The Pile)

Max Activating Token Index: 864

Text #4

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.9101. Min Act: 0.0001

Data Index: 1405364 (The Pile)

Max Activating Token Index: 900

Text #5

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.8459. Min Act: -0.0000

Data Index: 625211 (The Pile)

Max Activating Token Index: 735

Text #6

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.7681. Min Act: -0.0000

Data Index: 1271438 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.7289. Min Act: 0.0000

Data Index: 1691888 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.8144. Min Act: 0.0000

Data Index: 581018 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.7849. Min Act: 0.0000

Data Index: 899686 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.8267. Min Act: 0.0000

Data Index: 468469 (The Pile)

Max Activating Token Index: 286

Text #11

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.7641. Min Act: 0.0000

Data Index: 511996 (The Pile)

Max Activating Token Index: 715

Text #12

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.7160. Min Act: -0.0000

Data Index: 285770 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.7205. Min Act: -0.0000

Data Index: 171185 (The Pile)

Max Activating Token Index: 337

Text #14

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1568712 (The Pile)

Max Activating Token Index: 547

Text #15

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.6551. Min Act: -0.0000

Data Index: 767764 (The Pile)

Max Activating Token Index: 369

Text #16

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1291627 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1522272 (The Pile)

Max Activating Token Index: 213

Text #18

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.6491. Min Act: -0.0000

Data Index: 251427 (The Pile)

Max Activating Token Index: 861

Text #19

Max Range: 1.3813. Min Range: -1.3813

Max Act: 0.6412. Min Act: 0.0001

Data Index: 978675 (The Pile)

Max Activating Token Index: 569