Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 539 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6287. Min Act: -0.0000

Data Index: 388983 (The Pile)

Max Activating Token Index: 796

Text #1

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6001. Min Act: -0.0000

Data Index: 529467 (The Pile)

Max Activating Token Index: 504

Text #2

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1411784 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1803140 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6097. Min Act: -0.0000

Data Index: 544317 (The Pile)

Max Activating Token Index: 430

Text #5

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6260. Min Act: -0.0000

Data Index: 950390 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6052. Min Act: -0.0000

Data Index: 169999 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5809. Min Act: -0.0000

Data Index: 911709 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1777277 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1714699 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1488780 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5492. Min Act: -0.0000

Data Index: 419999 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1552756 (The Pile)

Max Activating Token Index: 419

Text #13

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1838211 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5717. Min Act: -0.0000

Data Index: 142372 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5710. Min Act: -0.0000

Data Index: 996691 (The Pile)

Max Activating Token Index: 378

Text #16

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1926486 (The Pile)

Max Activating Token Index: 401

Text #17

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5614. Min Act: -0.0000

Data Index: 29093 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5762. Min Act: -0.0000

Data Index: 316979 (The Pile)

Max Activating Token Index: 320

Text #19

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5433. Min Act: -0.0000

Data Index: 298961 (The Pile)

Max Activating Token Index: 903