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

Dataset: The Pile

Neuron 2413 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: 1.0517. Min Range: -1.0517

Max Act: 1.0517. Min Act: 0.0000

Data Index: 1261693 (The Pile)

Max Activating Token Index: 588

Text #1

Max Range: 1.0517. Min Range: -1.0517

Max Act: 1.0314. Min Act: -0.0000

Data Index: 163163 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 1.0517. Min Range: -1.0517

Max Act: 1.0510. Min Act: -0.0000

Data Index: 185812 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 1.0517. Min Range: -1.0517

Max Act: 1.0230. Min Act: -0.0000

Data Index: 345311 (The Pile)

Max Activating Token Index: 498

Text #4

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9936. Min Act: -0.0000

Data Index: 607084 (The Pile)

Max Activating Token Index: 486

Text #5

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9982. Min Act: -0.0000

Data Index: 841972 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1920335 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9693. Min Act: -0.0000

Data Index: 771733 (The Pile)

Max Activating Token Index: 340

Text #8

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1630572 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9188. Min Act: -0.0000

Data Index: 124109 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9579. Min Act: -0.0000

Data Index: 356241 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1601173 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9167. Min Act: -0.0000

Data Index: 898093 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9652. Min Act: -0.0000

Data Index: 501943 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1956479 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9701. Min Act: -0.0000

Data Index: 656354 (The Pile)

Max Activating Token Index: 759

Text #16

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1996613 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8945. Min Act: -0.0000

Data Index: 266337 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9202. Min Act: -0.0000

Data Index: 488912 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1264821 (The Pile)

Max Activating Token Index: 42