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

Dataset: The Pile

Neuron 4354 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.9331. Min Act: -0.0000

Data Index: 1402942 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.7600. Min Act: -0.0000

Data Index: 1224177 (The Pile)

Max Activating Token Index: 888

Text #2

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.8005. Min Act: -0.0000

Data Index: 999856 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6213. Min Act: -0.0000

Data Index: 385298 (The Pile)

Max Activating Token Index: 614

Text #4

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6079. Min Act: -0.0000

Data Index: 1513546 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6578. Min Act: -0.0000

Data Index: 1602232 (The Pile)

Max Activating Token Index: 449

Text #6

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6891. Min Act: -0.0000

Data Index: 255534 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6372. Min Act: -0.0000

Data Index: 1328992 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6513. Min Act: -0.0000

Data Index: 1844495 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6507. Min Act: -0.0000

Data Index: 448576 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.5544. Min Act: -0.0000

Data Index: 1230391 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.5240. Min Act: -0.0000

Data Index: 1354076 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.5666. Min Act: -0.0000

Data Index: 1207880 (The Pile)

Max Activating Token Index: 421

Text #13

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.5496. Min Act: -0.0000

Data Index: 860034 (The Pile)

Max Activating Token Index: 798

Text #14

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.6447. Min Act: -0.0000

Data Index: 835917 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.5771. Min Act: -0.0000

Data Index: 431399 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.4738. Min Act: -0.0000

Data Index: 1112240 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.4809. Min Act: -0.0000

Data Index: 1981458 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.3278. Min Act: -0.0000

Data Index: 1312152 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 1.9331. Min Range: -1.9331

Max Act: 1.5303. Min Act: -0.0000

Data Index: 1360278 (The Pile)

Max Activating Token Index: 609