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

Dataset: The Pile

Neuron 3415 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3833. Min Range: -1.3833

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1685982 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 1.3833. Min Range: -1.3833

Max Act: 1.1830. Min Act: -0.0000

Data Index: 715678 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 1.3833. Min Range: -1.3833

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1600133 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 1.3833. Min Range: -1.3833

Max Act: 1.0678. Min Act: -0.0000

Data Index: 191459 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 1.3833. Min Range: -1.3833

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1429062 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.9694. Min Act: -0.0000

Data Index: 462770 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1879141 (The Pile)

Max Activating Token Index: 612

Text #7

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.9246. Min Act: -0.0000

Data Index: 574120 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1222942 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.9627. Min Act: -0.0000

Data Index: 1348025 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.9358. Min Act: -0.0000

Data Index: 1076334 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1253409 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1900158 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1334712 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.7788. Min Act: -0.0000

Data Index: 129379 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.7410. Min Act: -0.0000

Data Index: 344917 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.7649. Min Act: -0.0000

Data Index: 50818 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1206523 (The Pile)

Max Activating Token Index: 442

Text #18

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.7913. Min Act: -0.0000

Data Index: 493797 (The Pile)

Max Activating Token Index: 384

Text #19

Max Range: 1.3833. Min Range: -1.3833

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1728519 (The Pile)

Max Activating Token Index: 306