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

Dataset: The Pile

Neuron 4627 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.9777. Min Act: -0.0000

Data Index: 1708523 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.8160. Min Act: -0.0000

Data Index: 808082 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.9642. Min Act: -0.0000

Data Index: 338878 (The Pile)

Max Activating Token Index: 163

Text #3

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.6992. Min Act: -0.0000

Data Index: 390316 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7472. Min Act: -0.0000

Data Index: 1035145 (The Pile)

Max Activating Token Index: 582

Text #5

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7261. Min Act: -0.0000

Data Index: 1489378 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.8624. Min Act: -0.0000

Data Index: 1855116 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7484. Min Act: -0.0000

Data Index: 650802 (The Pile)

Max Activating Token Index: 323

Text #8

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7523. Min Act: -0.0000

Data Index: 1438226 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.9988. Min Act: -0.0000

Data Index: 485699 (The Pile)

Max Activating Token Index: 369

Text #10

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7602. Min Act: -0.0000

Data Index: 757870 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1854134 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7466. Min Act: -0.0000

Data Index: 533568 (The Pile)

Max Activating Token Index: 319

Text #13

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.6220. Min Act: -0.0000

Data Index: 696059 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.6317. Min Act: -0.0000

Data Index: 1187319 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.6845. Min Act: -0.0000

Data Index: 1040538 (The Pile)

Max Activating Token Index: 337

Text #16

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.6511. Min Act: -0.0000

Data Index: 1162965 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.3684. Min Act: -0.0000

Data Index: 1819457 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.6005. Min Act: -0.0000

Data Index: 760913 (The Pile)

Max Activating Token Index: 842

Text #19

Max Range: 1.9988. Min Range: -1.9988

Max Act: 1.7486. Min Act: -0.0000

Data Index: 1477352 (The Pile)

Max Activating Token Index: 235