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

Dataset: The Pile

Neuron 555 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: 3.5725. Min Range: -3.5725

Max Act: 3.2347. Min Act: -0.0000

Data Index: 964354 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.1282. Min Act: -0.0000

Data Index: 1635580 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.5725. Min Act: -0.0000

Data Index: 199432 (The Pile)

Max Activating Token Index: 373

Text #3

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.5091. Min Act: -0.0000

Data Index: 492499 (The Pile)

Max Activating Token Index: 463

Text #4

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.3178. Min Act: -0.0000

Data Index: 1316133 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.1616. Min Act: -0.0000

Data Index: 393710 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.1655. Min Act: -0.0000

Data Index: 598868 (The Pile)

Max Activating Token Index: 258

Text #7

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.1938. Min Act: -0.0000

Data Index: 1199142 (The Pile)

Max Activating Token Index: 420

Text #8

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.1511. Min Act: -0.0000

Data Index: 1685764 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.0046. Min Act: -0.0000

Data Index: 1205247 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.1220. Min Act: -0.0000

Data Index: 1627465 (The Pile)

Max Activating Token Index: 73

Text #11

Max Range: 3.5725. Min Range: -3.5725

Max Act: 2.9697. Min Act: -0.0000

Data Index: 924678 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 3.5725. Min Range: -3.5725

Max Act: 3.0020. Min Act: -0.0000

Data Index: 745915 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 3.5725. Min Range: -3.5725

Max Act: 2.8370. Min Act: -0.0000

Data Index: 1842613 (The Pile)

Max Activating Token Index: 557

Text #14

Max Range: 3.5725. Min Range: -3.5725

Max Act: 2.8050. Min Act: -0.0000

Data Index: 1358907 (The Pile)

Max Activating Token Index: 285

Text #15

Max Range: 3.5725. Min Range: -3.5725

Max Act: 2.7791. Min Act: -0.0000

Data Index: 1792823 (The Pile)

Max Activating Token Index: 255

Text #16

Max Range: 3.5725. Min Range: -3.5725

Max Act: 2.7761. Min Act: -0.0000

Data Index: 118364 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 3.5725. Min Range: -3.5725

Max Act: 2.9245. Min Act: -0.0000

Data Index: 542405 (The Pile)

Max Activating Token Index: 235

Text #18

Max Range: 3.5725. Min Range: -3.5725

Max Act: 2.6104. Min Act: -0.0000

Data Index: 1057648 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 3.5725. Min Range: -3.5725

Max Act: 2.8177. Min Act: -0.0000

Data Index: 775961 (The Pile)

Max Activating Token Index: 233