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

Dataset: The Pile

Neuron 496 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.7642. Min Act: -0.0000

Data Index: 1217328 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.5254. Min Act: -0.0000

Data Index: 476363 (The Pile)

Max Activating Token Index: 328

Text #2

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.5102. Min Act: -0.0000

Data Index: 79134 (The Pile)

Max Activating Token Index: 5

Text #3

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.4912. Min Act: -0.0000

Data Index: 1543554 (The Pile)

Max Activating Token Index: 689

Text #4

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.5795. Min Act: -0.0000

Data Index: 552792 (The Pile)

Max Activating Token Index: 939

Text #5

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.4576. Min Act: -0.0000

Data Index: 1592363 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3302. Min Act: -0.0000

Data Index: 812294 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3220. Min Act: -0.0000

Data Index: 199287 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1469035 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1238813 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1792618 (The Pile)

Max Activating Token Index: 997

Text #11

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.4130. Min Act: -0.0000

Data Index: 1471336 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1479506 (The Pile)

Max Activating Token Index: 76

Text #13

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3141. Min Act: -0.0000

Data Index: 1815055 (The Pile)

Max Activating Token Index: 692

Text #14

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3225. Min Act: -0.0000

Data Index: 724382 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1712454 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.2268. Min Act: -0.0000

Data Index: 672426 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.2843. Min Act: -0.0000

Data Index: 1708456 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1301360 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 1.7642. Min Range: -1.7642

Max Act: 1.2802. Min Act: -0.0000

Data Index: 269699 (The Pile)

Max Activating Token Index: 917