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

Dataset: The Pile

Neuron 1159 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.5859. Min Act: -0.0000

Data Index: 1046251 (The Pile)

Max Activating Token Index: 603

Text #1

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.2629. Min Act: -0.0000

Data Index: 449724 (The Pile)

Max Activating Token Index: 964

Text #2

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.8903. Min Act: -0.0000

Data Index: 1686378 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.9129. Min Act: -0.0000

Data Index: 999853 (The Pile)

Max Activating Token Index: 1002

Text #4

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.8696. Min Act: -0.0000

Data Index: 894809 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 1.5859. Min Range: -1.5859

Max Act: 1.0031. Min Act: -0.0000

Data Index: 1343476 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1227655 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.8517. Min Act: -0.0000

Data Index: 657959 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.7681. Min Act: -0.0000

Data Index: 431577 (The Pile)

Max Activating Token Index: 590

Text #9

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.7992. Min Act: -0.0000

Data Index: 708017 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1918408 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.6793. Min Act: -0.0000

Data Index: 443539 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1333459 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1780629 (The Pile)

Max Activating Token Index: 97

Text #14

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.7628. Min Act: -0.0000

Data Index: 135036 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.6873. Min Act: -0.0000

Data Index: 178378 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1777416 (The Pile)

Max Activating Token Index: 775

Text #17

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.6119. Min Act: -0.0000

Data Index: 723987 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.7137. Min Act: -0.0000

Data Index: 742081 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 1.5859. Min Range: -1.5859

Max Act: 0.6442. Min Act: -0.0000

Data Index: 543679 (The Pile)

Max Activating Token Index: 390