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

Dataset: The Pile

Neuron 4117 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1011918 (The Pile)

Max Activating Token Index: 717

Text #1

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1985112 (The Pile)

Max Activating Token Index: 495

Text #2

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5652. Min Act: -0.0000

Data Index: 748336 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5205. Min Act: -0.0000

Data Index: 743848 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1279400 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1898427 (The Pile)

Max Activating Token Index: 304

Text #6

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4793. Min Act: -0.0000

Data Index: 675181 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4908. Min Act: -0.0000

Data Index: 691495 (The Pile)

Max Activating Token Index: 49

Text #8

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4937. Min Act: -0.0000

Data Index: 184202 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1481728 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4358. Min Act: -0.0000

Data Index: 264212 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4404. Min Act: -0.0000

Data Index: 443138 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1651055 (The Pile)

Max Activating Token Index: 63

Text #13

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1643642 (The Pile)

Max Activating Token Index: 7

Text #14

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4219. Min Act: -0.0000

Data Index: 966424 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1763346 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4261. Min Act: -0.0000

Data Index: 117971 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4237. Min Act: -0.0000

Data Index: 681744 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1621869 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4444. Min Act: -0.0000

Data Index: 682749 (The Pile)

Max Activating Token Index: 854