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

Dataset: The Pile

Neuron 421 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.1310. Min Act: -0.0000

Data Index: 654345 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.0197. Min Act: -0.0000

Data Index: 119438 (The Pile)

Max Activating Token Index: 736

Text #2

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9904. Min Act: -0.0000

Data Index: 168624 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1299838 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1228333 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1495347 (The Pile)

Max Activating Token Index: 452

Text #6

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8665. Min Act: -0.0000

Data Index: 176299 (The Pile)

Max Activating Token Index: 452

Text #7

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9168. Min Act: -0.0000

Data Index: 680850 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8833. Min Act: -0.0000

Data Index: 42931 (The Pile)

Max Activating Token Index: 591

Text #9

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9065. Min Act: -0.0000

Data Index: 341001 (The Pile)

Max Activating Token Index: 558

Text #10

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1500498 (The Pile)

Max Activating Token Index: 575

Text #11

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8987. Min Act: -0.0000

Data Index: 129767 (The Pile)

Max Activating Token Index: 771

Text #12

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8847. Min Act: -0.0000

Data Index: 795470 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8393. Min Act: -0.0000

Data Index: 716347 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1730779 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8845. Min Act: -0.0000

Data Index: 1991272 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1437814 (The Pile)

Max Activating Token Index: 93

Text #17

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8757. Min Act: -0.0000

Data Index: 392421 (The Pile)

Max Activating Token Index: 412

Text #18

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8158. Min Act: -0.0000

Data Index: 780496 (The Pile)

Max Activating Token Index: 619

Text #19

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1629805 (The Pile)

Max Activating Token Index: 432