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

Dataset: The Pile

Neuron 1920 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: 0.5582. Min Range: -0.5582

Max Act: 0.5582. Min Act: -0.0000

Data Index: 910378 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4835. Min Act: -0.0000

Data Index: 1357048 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4883. Min Act: -0.0000

Data Index: 398188 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4330. Min Act: -0.0000

Data Index: 335143 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4580. Min Act: -0.0000

Data Index: 780922 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1016625 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1834752 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1059740 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3790. Min Act: -0.0000

Data Index: 415632 (The Pile)

Max Activating Token Index: 981

Text #9

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4125. Min Act: -0.0000

Data Index: 143938 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1779030 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4210. Min Act: -0.0000

Data Index: 984688 (The Pile)

Max Activating Token Index: 401

Text #12

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1436753 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1392509 (The Pile)

Max Activating Token Index: 898

Text #14

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3997. Min Act: -0.0000

Data Index: 578836 (The Pile)

Max Activating Token Index: 535

Text #15

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1826102 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3730. Min Act: -0.0000

Data Index: 875737 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1599542 (The Pile)

Max Activating Token Index: 381

Text #18

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1803805 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1362667 (The Pile)

Max Activating Token Index: 294