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

Dataset: The Pile

Neuron 715 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5429. Min Act: -0.0000

Data Index: 919176 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.6006. Min Act: -0.0000

Data Index: 613188 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1087603 (The Pile)

Max Activating Token Index: 528

Text #3

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5498. Min Act: -0.0000

Data Index: 870306 (The Pile)

Max Activating Token Index: 415

Text #4

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1993106 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1688938 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4946. Min Act: -0.0000

Data Index: 514997 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1464725 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4929. Min Act: -0.0000

Data Index: 355940 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1761340 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1281970 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1329263 (The Pile)

Max Activating Token Index: 99

Text #12

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4391. Min Act: -0.0000

Data Index: 92245 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4786. Min Act: -0.0000

Data Index: 351849 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1127693 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1222941 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4609. Min Act: -0.0000

Data Index: 527376 (The Pile)

Max Activating Token Index: 832

Text #17

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1971870 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4420. Min Act: -0.0000

Data Index: 98150 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1822594 (The Pile)

Max Activating Token Index: 1010