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

Dataset: The Pile

Neuron 645 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: 5.8532. Min Range: -5.8532

Max Act: 5.8197. Min Act: -0.0000

Data Index: 1933764 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.4053. Min Act: -0.0000

Data Index: 889122 (The Pile)

Max Activating Token Index: 615

Text #2

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.5929. Min Act: -0.0000

Data Index: 1324164 (The Pile)

Max Activating Token Index: 896

Text #3

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.7418. Min Act: -0.0000

Data Index: 362199 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.5303. Min Act: -0.0000

Data Index: 746728 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.8532. Min Act: -0.0000

Data Index: 1078831 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.6732. Min Act: -0.0000

Data Index: 1468787 (The Pile)

Max Activating Token Index: 880

Text #7

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.6538. Min Act: -0.0000

Data Index: 118171 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.8281. Min Act: -0.0000

Data Index: 31560 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.6640. Min Act: -0.0000

Data Index: 857201 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.6330. Min Act: -0.0000

Data Index: 1285479 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.4216. Min Act: -0.0000

Data Index: 1901006 (The Pile)

Max Activating Token Index: 425

Text #12

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.4125. Min Act: -0.0000

Data Index: 24642 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.5539. Min Act: -0.0000

Data Index: 235214 (The Pile)

Max Activating Token Index: 588

Text #14

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.5590. Min Act: -0.0000

Data Index: 1477137 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.3646. Min Act: -0.0000

Data Index: 128038 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.4660. Min Act: -0.0000

Data Index: 1844989 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.5392. Min Act: -0.0000

Data Index: 731840 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.5213. Min Act: -0.0000

Data Index: 963953 (The Pile)

Max Activating Token Index: 583

Text #19

Max Range: 5.8532. Min Range: -5.8532

Max Act: 5.6765. Min Act: -0.0000

Data Index: 795452 (The Pile)

Max Activating Token Index: 401