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

Dataset: The Pile

Neuron 4893 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: 1.9766. Min Range: -1.9766

Max Act: 1.9766. Min Act: -0.0000

Data Index: 1276259 (The Pile)

Max Activating Token Index: 162

Text #1

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.9355. Min Act: -0.0000

Data Index: 1900231 (The Pile)

Max Activating Token Index: 18

Text #2

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7828. Min Act: -0.0000

Data Index: 638782 (The Pile)

Max Activating Token Index: 311

Text #3

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.6860. Min Act: -0.0000

Data Index: 1619289 (The Pile)

Max Activating Token Index: 41

Text #4

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.7748. Min Act: -0.0000

Data Index: 53898 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.5738. Min Act: -0.0000

Data Index: 25141 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.5833. Min Act: -0.0000

Data Index: 1219634 (The Pile)

Max Activating Token Index: 30

Text #7

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.6265. Min Act: -0.0000

Data Index: 251660 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.5411. Min Act: -0.0000

Data Index: 332925 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.6259. Min Act: -0.0000

Data Index: 442873 (The Pile)

Max Activating Token Index: 376

Text #10

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.5397. Min Act: -0.0000

Data Index: 157323 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.5991. Min Act: -0.0000

Data Index: 1738178 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.6347. Min Act: -0.0000

Data Index: 93656 (The Pile)

Max Activating Token Index: 582

Text #13

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.5020. Min Act: -0.0000

Data Index: 474049 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.4217. Min Act: -0.0000

Data Index: 270243 (The Pile)

Max Activating Token Index: 625

Text #15

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.5359. Min Act: -0.0000

Data Index: 1633957 (The Pile)

Max Activating Token Index: 302

Text #16

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.4184. Min Act: -0.0000

Data Index: 911524 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.5878. Min Act: -0.0000

Data Index: 1010842 (The Pile)

Max Activating Token Index: 760

Text #18

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.5927. Min Act: -0.0000

Data Index: 1633388 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 1.9766. Min Range: -1.9766

Max Act: 1.4954. Min Act: -0.0000

Data Index: 342721 (The Pile)

Max Activating Token Index: 58