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

Dataset: The Pile

Neuron 918 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: 0.8709. Min Range: -0.8709

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1117600 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.7059. Min Act: -0.0000

Data Index: 387207 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.6213. Min Act: -0.0000

Data Index: 837737 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.5326. Min Act: -0.0000

Data Index: 368138 (The Pile)

Max Activating Token Index: 698

Text #4

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.4907. Min Act: -0.0000

Data Index: 70893 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.4800. Min Act: -0.0000

Data Index: 361166 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.5274. Min Act: -0.0000

Data Index: 850158 (The Pile)

Max Activating Token Index: 359

Text #7

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.5084. Min Act: -0.0000

Data Index: 167072 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.4771. Min Act: -0.0000

Data Index: 767408 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.4669. Min Act: -0.0000

Data Index: 612342 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1025507 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1581379 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1874024 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.4032. Min Act: -0.0000

Data Index: 685989 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1773532 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.3740. Min Act: -0.0000

Data Index: 807583 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1713318 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.3925. Min Act: -0.0000

Data Index: 285980 (The Pile)

Max Activating Token Index: 836

Text #18

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.3265. Min Act: -0.0000

Data Index: 1190684 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 0.8709. Min Range: -0.8709

Max Act: 0.3862. Min Act: -0.0000

Data Index: 396443 (The Pile)

Max Activating Token Index: 732