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

Dataset: The Pile

Neuron 1694 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: 0.8239. Min Range: -0.8239

Max Act: 0.8239. Min Act: -0.0000

Data Index: 114666 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1655665 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1911195 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.7867. Min Act: -0.0000

Data Index: 293537 (The Pile)

Max Activating Token Index: 908

Text #4

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.8000. Min Act: -0.0000

Data Index: 976068 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1698519 (The Pile)

Max Activating Token Index: 698

Text #6

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6446. Min Act: -0.0000

Data Index: 705260 (The Pile)

Max Activating Token Index: 826

Text #7

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6800. Min Act: -0.0000

Data Index: 518020 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1467135 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1998166 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1833252 (The Pile)

Max Activating Token Index: 793

Text #11

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6930. Min Act: -0.0000

Data Index: 369290 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6627. Min Act: -0.0000

Data Index: 668028 (The Pile)

Max Activating Token Index: 521

Text #13

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6902. Min Act: -0.0000

Data Index: 393014 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1763996 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1190830 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1569051 (The Pile)

Max Activating Token Index: 838

Text #17

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6682. Min Act: -0.0000

Data Index: 55880 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1231053 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 0.8239. Min Range: -0.8239

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1230120 (The Pile)

Max Activating Token Index: 660