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

Dataset: The Pile

Neuron 3856 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: 1.0798. Min Range: -1.0798

Max Act: 1.0798. Min Act: -0.0000

Data Index: 484187 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 1.0798. Min Range: -1.0798

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1646028 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1354895 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1828410 (The Pile)

Max Activating Token Index: 436

Text #4

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9563. Min Act: -0.0000

Data Index: 309446 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1972261 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1705941 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9235. Min Act: -0.0000

Data Index: 765515 (The Pile)

Max Activating Token Index: 37

Text #8

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9216. Min Act: -0.0001

Data Index: 226536 (The Pile)

Max Activating Token Index: 9

Text #9

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1313395 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8905. Min Act: -0.0001

Data Index: 1227649 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1559596 (The Pile)

Max Activating Token Index: 488

Text #12

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8800. Min Act: -0.0001

Data Index: 681672 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1872681 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8263. Min Act: -0.0000

Data Index: 805950 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1070953 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1916859 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1882196 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.8566. Min Act: -0.0000

Data Index: 395144 (The Pile)

Max Activating Token Index: 641

Text #19

Max Range: 1.0798. Min Range: -1.0798

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1091493 (The Pile)

Max Activating Token Index: 211