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

Dataset: The Pile

Neuron 3539 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: 1.7232. Min Range: -1.7232

Max Act: 1.7232. Min Act: -0.0000

Data Index: 168414 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.3689. Min Act: -0.0000

Data Index: 939553 (The Pile)

Max Activating Token Index: 292

Text #2

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.3334. Min Act: -0.0000

Data Index: 1806674 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.2589. Min Act: -0.0000

Data Index: 1726731 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1406831 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1263521 (The Pile)

Max Activating Token Index: 871

Text #6

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.1945. Min Act: -0.0000

Data Index: 331233 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.2056. Min Act: -0.0000

Data Index: 306653 (The Pile)

Max Activating Token Index: 764

Text #8

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.1789. Min Act: -0.0000

Data Index: 626691 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.2746. Min Act: -0.0000

Data Index: 1720823 (The Pile)

Max Activating Token Index: 666

Text #10

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.0852. Min Act: -0.0000

Data Index: 1956235 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.1334. Min Act: -0.0000

Data Index: 265849 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.1273. Min Act: -0.0000

Data Index: 1064367 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1863000 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1079585 (The Pile)

Max Activating Token Index: 339

Text #15

Max Range: 1.7232. Min Range: -1.7232

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1726131 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.0394. Min Act: -0.0000

Data Index: 1104165 (The Pile)

Max Activating Token Index: 749

Text #17

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1859060 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 1.7232. Min Range: -1.7232

Max Act: 1.0473. Min Act: -0.0000

Data Index: 460646 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 1.7232. Min Range: -1.7232

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1675240 (The Pile)

Max Activating Token Index: 597