Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1850 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2665. Min Act: -0.0000

Data Index: 16512 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.2162. Min Act: -0.0000

Data Index: 805339 (The Pile)

Max Activating Token Index: 125

Text #2

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1945. Min Act: -0.0000

Data Index: 681334 (The Pile)

Max Activating Token Index: 259

Text #3

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1705614 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1808. Min Act: -0.0000

Data Index: 358918 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1813015 (The Pile)

Max Activating Token Index: 873

Text #6

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1851. Min Act: -0.0000

Data Index: 441579 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1776. Min Act: -0.0000

Data Index: 779658 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1542028 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1812082 (The Pile)

Max Activating Token Index: 431

Text #10

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1576. Min Act: -0.0000

Data Index: 49377 (The Pile)

Max Activating Token Index: 936

Text #11

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1741. Min Act: -0.0000

Data Index: 441104 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1670. Min Act: -0.0000

Data Index: 342096 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1186543 (The Pile)

Max Activating Token Index: 173

Text #14

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1579. Min Act: -0.0000

Data Index: 289520 (The Pile)

Max Activating Token Index: 88

Text #15

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1544. Min Act: -0.0000

Data Index: 432114 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1589. Min Act: -0.0000

Data Index: 338197 (The Pile)

Max Activating Token Index: 210

Text #17

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1690871 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1593. Min Act: -0.0000

Data Index: 396851 (The Pile)

Max Activating Token Index: 567

Text #19

Max Range: 0.2665. Min Range: -0.2665

Max Act: 0.1488. Min Act: -0.0000

Data Index: 1734853 (The Pile)

Max Activating Token Index: 656