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

Dataset: The Pile

Neuron 1553 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: 1.2256. Min Range: -1.2256

Max Act: 1.2256. Min Act: -0.0000

Data Index: 1674480 (The Pile)

Max Activating Token Index: 32

Text #1

Max Range: 1.2256. Min Range: -1.2256

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1529364 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 1.2256. Min Range: -1.2256

Max Act: 1.0783. Min Act: -0.0000

Data Index: 861793 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.9977. Min Act: -0.0000

Data Index: 166805 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1514847 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1434643 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.9611. Min Act: -0.0000

Data Index: 104018 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.9447. Min Act: -0.0000

Data Index: 980323 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.9226. Min Act: -0.0000

Data Index: 135148 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.8575. Min Act: -0.0000

Data Index: 293003 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.9969. Min Act: -0.0000

Data Index: 1870844 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1382354 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.9316. Min Act: -0.0000

Data Index: 442650 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1428429 (The Pile)

Max Activating Token Index: 89

Text #14

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1481420 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.8871. Min Act: -0.0000

Data Index: 717550 (The Pile)

Max Activating Token Index: 1009

Text #16

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.9130. Min Act: -0.0000

Data Index: 342797 (The Pile)

Max Activating Token Index: 421

Text #17

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.8625. Min Act: -0.0000

Data Index: 602909 (The Pile)

Max Activating Token Index: 518

Text #18

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1612455 (The Pile)

Max Activating Token Index: 784

Text #19

Max Range: 1.2256. Min Range: -1.2256

Max Act: 0.9852. Min Act: -0.0000

Data Index: 133312 (The Pile)

Max Activating Token Index: 913