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

Dataset: The Pile

Neuron 1932 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.5637. Min Act: -0.0000

Data Index: 882636 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.5037. Min Act: -0.0000

Data Index: 967979 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1815245 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1005708 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1994163 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4657. Min Act: -0.0000

Data Index: 473850 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1014750 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4248. Min Act: -0.0000

Data Index: 720617 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1716796 (The Pile)

Max Activating Token Index: 147

Text #9

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1865872 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1855998 (The Pile)

Max Activating Token Index: 809

Text #11

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4245. Min Act: -0.0000

Data Index: 130888 (The Pile)

Max Activating Token Index: 915

Text #12

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4842. Min Act: -0.0000

Data Index: 457121 (The Pile)

Max Activating Token Index: 86

Text #13

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1043057 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1575090 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1706279 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4193. Min Act: -0.0000

Data Index: 702254 (The Pile)

Max Activating Token Index: 951

Text #17

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1986713 (The Pile)

Max Activating Token Index: 143

Text #18

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.3927. Min Act: -0.0000

Data Index: 309396 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 0.5637. Min Range: -0.5637

Max Act: 0.4059. Min Act: -0.0000

Data Index: 753743 (The Pile)

Max Activating Token Index: 581