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

Dataset: The Pile

Neuron 2251 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.2824. Min Act: -0.0000

Data Index: 1822099 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1413522 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.1421. Min Act: -0.0000

Data Index: 590711 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.1851. Min Act: -0.0000

Data Index: 1739480 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.1112. Min Act: -0.0000

Data Index: 291108 (The Pile)

Max Activating Token Index: 989

Text #5

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1805990 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1000758 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1840445 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9499. Min Act: -0.0000

Data Index: 758585 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.0067. Min Act: -0.0000

Data Index: 1509360 (The Pile)

Max Activating Token Index: 85

Text #10

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9589. Min Act: -0.0000

Data Index: 919519 (The Pile)

Max Activating Token Index: 840

Text #11

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1039735 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1310632 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8924. Min Act: -0.0000

Data Index: 566628 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1203545 (The Pile)

Max Activating Token Index: 711

Text #15

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9455. Min Act: -0.0000

Data Index: 960109 (The Pile)

Max Activating Token Index: 581

Text #16

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8730. Min Act: -0.0000

Data Index: 762451 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8684. Min Act: -0.0000

Data Index: 502114 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9231. Min Act: -0.0000

Data Index: 1818197 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1338240 (The Pile)

Max Activating Token Index: 975