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

Dataset: The Pile

Neuron 151 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: 1.6623. Min Range: -1.6623

Max Act: 1.6623. Min Act: -0.0000

Data Index: 1385689 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.5364. Min Act: -0.0000

Data Index: 1883479 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.3980. Min Act: -0.0000

Data Index: 1591804 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.5431. Min Act: -0.0000

Data Index: 1218592 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.3847. Min Act: -0.0000

Data Index: 1329389 (The Pile)

Max Activating Token Index: 208

Text #5

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.3604. Min Act: -0.0000

Data Index: 946913 (The Pile)

Max Activating Token Index: 104

Text #6

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.3212. Min Act: -0.0000

Data Index: 653901 (The Pile)

Max Activating Token Index: 672

Text #7

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.3343. Min Act: -0.0000

Data Index: 348436 (The Pile)

Max Activating Token Index: 713

Text #8

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2966. Min Act: -0.0000

Data Index: 147313 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2835. Min Act: -0.0000

Data Index: 1065906 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1320978 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.3043. Min Act: -0.0000

Data Index: 467214 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.0890. Min Act: -0.0000

Data Index: 1013789 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2871. Min Act: -0.0000

Data Index: 384676 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1252691 (The Pile)

Max Activating Token Index: 104

Text #15

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1677834 (The Pile)

Max Activating Token Index: 143

Text #16

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1075743 (The Pile)

Max Activating Token Index: 549

Text #17

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.0218. Min Act: -0.0000

Data Index: 964912 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.0478. Min Act: -0.0000

Data Index: 197618 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 1.6623. Min Range: -1.6623

Max Act: 1.2381. Min Act: -0.0000

Data Index: 1996053 (The Pile)

Max Activating Token Index: 621