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

Dataset: The Pile

Neuron 573 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: 1.1279. Min Range: -1.1279

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1721340 (The Pile)

Max Activating Token Index: 809

Text #1

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.8394. Min Act: -0.0000

Data Index: 530722 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 1.1279. Min Range: -1.1279

Max Act: 1.1279. Min Act: -0.0000

Data Index: 1048738 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.6621. Min Act: -0.0000

Data Index: 975331 (The Pile)

Max Activating Token Index: 177

Text #4

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1325517 (The Pile)

Max Activating Token Index: 474

Text #5

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1769377 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.7017. Min Act: -0.0000

Data Index: 1658128 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.4737. Min Act: -0.0000

Data Index: 487786 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1535727 (The Pile)

Max Activating Token Index: 70

Text #9

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1220541 (The Pile)

Max Activating Token Index: 124

Text #10

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1234865 (The Pile)

Max Activating Token Index: 582

Text #11

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1533490 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1426486 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.5727. Min Act: -0.0000

Data Index: 542358 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1458450 (The Pile)

Max Activating Token Index: 649

Text #15

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1695237 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.4513. Min Act: -0.0000

Data Index: 777707 (The Pile)

Max Activating Token Index: 808

Text #17

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1381485 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1150672 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 1.1279. Min Range: -1.1279

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1861228 (The Pile)

Max Activating Token Index: 541