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

Dataset: The Pile

Neuron 1813 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.7648. Min Act: -0.0000

Data Index: 1061676 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.5989. Min Act: -0.0000

Data Index: 673436 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.9294. Min Act: -0.0000

Data Index: 1662226 (The Pile)

Max Activating Token Index: 682

Text #3

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.5888. Min Act: -0.0000

Data Index: 1537872 (The Pile)

Max Activating Token Index: 499

Text #4

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.5251. Min Act: -0.0000

Data Index: 490299 (The Pile)

Max Activating Token Index: 506

Text #5

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.4904. Min Act: -0.0000

Data Index: 641205 (The Pile)

Max Activating Token Index: 934

Text #6

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.0606. Min Act: -0.0000

Data Index: 226236 (The Pile)

Max Activating Token Index: 597

Text #7

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.8094. Min Act: -0.0000

Data Index: 447795 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.5374. Min Act: -0.0000

Data Index: 30917 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.0018. Min Act: -0.0000

Data Index: 669162 (The Pile)

Max Activating Token Index: 401

Text #10

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.1621. Min Act: -0.0000

Data Index: 1794203 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.1397. Min Act: -0.0000

Data Index: 1247228 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 3.9294. Min Range: -3.9294

Max Act: 2.7308. Min Act: -0.0000

Data Index: 979595 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 3.9294. Min Range: -3.9294

Max Act: 2.7417. Min Act: -0.0000

Data Index: 1347702 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 3.9294. Min Range: -3.9294

Max Act: 2.8323. Min Act: -0.0000

Data Index: 1012432 (The Pile)

Max Activating Token Index: 808

Text #15

Max Range: 3.9294. Min Range: -3.9294

Max Act: 2.9648. Min Act: -0.0000

Data Index: 1539855 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 3.9294. Min Range: -3.9294

Max Act: 2.9762. Min Act: -0.0000

Data Index: 1267981 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 3.9294. Min Range: -3.9294

Max Act: 2.9664. Min Act: -0.0000

Data Index: 1491434 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.0495. Min Act: -0.0000

Data Index: 619831 (The Pile)

Max Activating Token Index: 627

Text #19

Max Range: 3.9294. Min Range: -3.9294

Max Act: 3.3059. Min Act: -0.0000

Data Index: 1516500 (The Pile)

Max Activating Token Index: 377