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

Dataset: The Pile

Neuron 2320 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: 0.9694. Min Range: -0.9694

Max Act: 0.9694. Min Act: -0.0000

Data Index: 431193 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1275078 (The Pile)

Max Activating Token Index: 865

Text #2

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1562684 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7516. Min Act: -0.0000

Data Index: 681540 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.8376. Min Act: -0.0000

Data Index: 1909642 (The Pile)

Max Activating Token Index: 675

Text #5

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7558. Min Act: -0.0000

Data Index: 301324 (The Pile)

Max Activating Token Index: 45

Text #6

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1988206 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1745741 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1300346 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1715886 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1805456 (The Pile)

Max Activating Token Index: 942

Text #11

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1768501 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1760988 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1737917 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6877. Min Act: -0.0000

Data Index: 556388 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6741. Min Act: -0.0000

Data Index: 161954 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1064235 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1573012 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6575. Min Act: -0.0000

Data Index: 675608 (The Pile)

Max Activating Token Index: 772

Text #19

Max Range: 0.9694. Min Range: -0.9694

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1188984 (The Pile)

Max Activating Token Index: 785