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

Dataset: The Pile

Neuron 1665 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: 6.4217. Min Range: -6.4217

Max Act: 6.4217. Min Act: -0.0001

Data Index: 1429858 (The Pile)

Max Activating Token Index: 902

Text #1

Max Range: 6.4217. Min Range: -6.4217

Max Act: 6.3067. Min Act: -0.0000

Data Index: 1187433 (The Pile)

Max Activating Token Index: 509

Text #2

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.3951. Min Act: -0.0000

Data Index: 1911561 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.5789. Min Act: -0.0000

Data Index: 919167 (The Pile)

Max Activating Token Index: 431

Text #4

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.5307. Min Act: -0.0000

Data Index: 857794 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.2101. Min Act: -0.0000

Data Index: 395554 (The Pile)

Max Activating Token Index: 376

Text #6

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.1417. Min Act: -0.0000

Data Index: 1113514 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.4849. Min Act: -0.0000

Data Index: 633652 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.0652. Min Act: -0.0000

Data Index: 1917516 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.1690. Min Act: -0.0000

Data Index: 526128 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.2735. Min Act: -0.0000

Data Index: 645087 (The Pile)

Max Activating Token Index: 648

Text #11

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.8617. Min Act: -0.0000

Data Index: 137533 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 6.4217. Min Range: -6.4217

Max Act: 5.0534. Min Act: -0.0000

Data Index: 323889 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.9909. Min Act: -0.0000

Data Index: 1820249 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.9715. Min Act: -0.0000

Data Index: 1382827 (The Pile)

Max Activating Token Index: 455

Text #15

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.8515. Min Act: -0.0000

Data Index: 1316860 (The Pile)

Max Activating Token Index: 899

Text #16

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.4528. Min Act: -0.0000

Data Index: 1266317 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.6562. Min Act: -0.0000

Data Index: 84971 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.4195. Min Act: -0.0000

Data Index: 424652 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 6.4217. Min Range: -6.4217

Max Act: 4.7359. Min Act: -0.0000

Data Index: 536699 (The Pile)

Max Activating Token Index: 252