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

Dataset: The Pile

Neuron 3345 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: 3.0256. Min Range: -3.0256

Max Act: 3.0256. Min Act: -0.0000

Data Index: 889958 (The Pile)

Max Activating Token Index: 722

Text #1

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.4865. Min Act: -0.0000

Data Index: 278843 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.4131. Min Act: -0.0000

Data Index: 1359027 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.2777. Min Act: -0.0000

Data Index: 437536 (The Pile)

Max Activating Token Index: 128

Text #4

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.1394. Min Act: -0.0000

Data Index: 933613 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.3649. Min Act: -0.0000

Data Index: 129115 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.4590. Min Act: -0.0000

Data Index: 1681653 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.1872. Min Act: -0.0000

Data Index: 1858534 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.1935. Min Act: -0.0000

Data Index: 1934793 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.1867. Min Act: -0.0000

Data Index: 1055773 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.0723. Min Act: -0.0000

Data Index: 1652067 (The Pile)

Max Activating Token Index: 930

Text #11

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.1655. Min Act: -0.0000

Data Index: 598683 (The Pile)

Max Activating Token Index: 431

Text #12

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.1679. Min Act: -0.0000

Data Index: 427551 (The Pile)

Max Activating Token Index: 328

Text #13

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.0484. Min Act: -0.0000

Data Index: 1125112 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.2612. Min Act: -0.0000

Data Index: 1545045 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 3.0256. Min Range: -3.0256

Max Act: 1.9866. Min Act: -0.0000

Data Index: 364464 (The Pile)

Max Activating Token Index: 848

Text #16

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.1974. Min Act: -0.0000

Data Index: 1176100 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 3.0256. Min Range: -3.0256

Max Act: 1.9868. Min Act: -0.0000

Data Index: 1603554 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 3.0256. Min Range: -3.0256

Max Act: 1.9612. Min Act: -0.0000

Data Index: 544894 (The Pile)

Max Activating Token Index: 894

Text #19

Max Range: 3.0256. Min Range: -3.0256

Max Act: 2.1909. Min Act: -0.0000

Data Index: 865455 (The Pile)

Max Activating Token Index: 525