Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3622 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.3608. Min Act: -0.0000

Data Index: 1334709 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1004727 (The Pile)

Max Activating Token Index: 414

Text #2

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.3687. Min Act: -0.0000

Data Index: 995073 (The Pile)

Max Activating Token Index: 713

Text #3

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.2902. Min Act: -0.0000

Data Index: 507027 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.1797. Min Act: -0.0000

Data Index: 1450548 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.2484. Min Act: -0.0000

Data Index: 32028 (The Pile)

Max Activating Token Index: 685

Text #6

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.2008. Min Act: -0.0000

Data Index: 1583531 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.0701. Min Act: -0.0000

Data Index: 1848446 (The Pile)

Max Activating Token Index: 871

Text #8

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1534820 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.1252. Min Act: -0.0000

Data Index: 1242578 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.0294. Min Act: -0.0000

Data Index: 102664 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.0339. Min Act: -0.0000

Data Index: 831291 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 1.3687. Min Range: -1.3687

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1533349 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1595406 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 1.3687. Min Range: -1.3687

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1779320 (The Pile)

Max Activating Token Index: 627

Text #15

Max Range: 1.3687. Min Range: -1.3687

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1724575 (The Pile)

Max Activating Token Index: 599

Text #16

Max Range: 1.3687. Min Range: -1.3687

Max Act: 0.9772. Min Act: -0.0000

Data Index: 965350 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 1.3687. Min Range: -1.3687

Max Act: 0.9929. Min Act: -0.0000

Data Index: 704560 (The Pile)

Max Activating Token Index: 696

Text #18

Max Range: 1.3687. Min Range: -1.3687

Max Act: 0.9421. Min Act: -0.0000

Data Index: 401046 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 1.3687. Min Range: -1.3687

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1699926 (The Pile)

Max Activating Token Index: 758