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

Dataset: The Pile

Neuron 2422 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: 0.2285. Min Range: -0.2285

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1609339 (The Pile)

Max Activating Token Index: 803

Text #1

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2278. Min Act: -0.0000

Data Index: 66948 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1742505 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1837173 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1913693 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1527. Min Act: -0.0000

Data Index: 921770 (The Pile)

Max Activating Token Index: 704

Text #6

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1819006 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1609. Min Act: -0.0000

Data Index: 831193 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1644. Min Act: -0.0000

Data Index: 954961 (The Pile)

Max Activating Token Index: 347

Text #9

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1672. Min Act: -0.0000

Data Index: 735404 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1515746 (The Pile)

Max Activating Token Index: 470

Text #11

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1454879 (The Pile)

Max Activating Token Index: 44

Text #12

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1612. Min Act: -0.0000

Data Index: 429867 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1590. Min Act: -0.0000

Data Index: 110997 (The Pile)

Max Activating Token Index: 283

Text #14

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1554. Min Act: -0.0000

Data Index: 680786 (The Pile)

Max Activating Token Index: 467

Text #15

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1273797 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1531. Min Act: -0.0000

Data Index: 778833 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1352. Min Act: -0.0000

Data Index: 791615 (The Pile)

Max Activating Token Index: 1022

Text #18

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1329946 (The Pile)

Max Activating Token Index: 516

Text #19

Max Range: 0.2285. Min Range: -0.2285

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1886763 (The Pile)

Max Activating Token Index: 412