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

Dataset: The Pile

Neuron 742 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: 1.6792. Min Range: -1.6792

Max Act: 1.6792. Min Act: -0.0000

Data Index: 1011574 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.3978. Min Act: -0.0000

Data Index: 881821 (The Pile)

Max Activating Token Index: 971

Text #2

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.6112. Min Act: -0.0000

Data Index: 1575464 (The Pile)

Max Activating Token Index: 550

Text #3

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.4745. Min Act: -0.0000

Data Index: 275534 (The Pile)

Max Activating Token Index: 882

Text #4

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.2198. Min Act: -0.0000

Data Index: 515408 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.2764. Min Act: -0.0000

Data Index: 1972354 (The Pile)

Max Activating Token Index: 463

Text #6

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1340970 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.9942. Min Act: -0.0000

Data Index: 926507 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 1.6792. Min Range: -1.6792

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1097269 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1750931 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1005098 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1241290 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.8374. Min Act: 0.0000

Data Index: 1503742 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.7975. Min Act: 0.0000

Data Index: 1361861 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.7214. Min Act: -0.0000

Data Index: 122252 (The Pile)

Max Activating Token Index: 543

Text #15

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.7264. Min Act: 0.0000

Data Index: 793452 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1716649 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.7331. Min Act: 0.0000

Data Index: 327110 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1576446 (The Pile)

Max Activating Token Index: 586

Text #19

Max Range: 1.6792. Min Range: -1.6792

Max Act: 0.7278. Min Act: 0.0001

Data Index: 457403 (The Pile)

Max Activating Token Index: 718