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

Dataset: The Pile

Neuron 140 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: 1.7801. Min Range: -1.7801

Max Act: 1.7801. Min Act: -0.0000

Data Index: 475001 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.7761. Min Act: -0.0000

Data Index: 1494234 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.6533. Min Act: -0.0000

Data Index: 1960585 (The Pile)

Max Activating Token Index: 919

Text #3

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.5909. Min Act: -0.0000

Data Index: 1656389 (The Pile)

Max Activating Token Index: 48

Text #4

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.6380. Min Act: -0.0000

Data Index: 1707135 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.6239. Min Act: -0.0000

Data Index: 1246772 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.6018. Min Act: -0.0000

Data Index: 1345275 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.5903. Min Act: -0.0000

Data Index: 1804781 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.5744. Min Act: -0.0000

Data Index: 1225735 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.5707. Min Act: -0.0000

Data Index: 997009 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1559323 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.5215. Min Act: -0.0000

Data Index: 1267517 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.4967. Min Act: -0.0000

Data Index: 391919 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.4729. Min Act: -0.0000

Data Index: 1099368 (The Pile)

Max Activating Token Index: 37

Text #14

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.4589. Min Act: -0.0000

Data Index: 1545724 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.5319. Min Act: -0.0000

Data Index: 455614 (The Pile)

Max Activating Token Index: 696

Text #16

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1717189 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.4132. Min Act: -0.0000

Data Index: 1842498 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.4128. Min Act: -0.0000

Data Index: 1239876 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 1.7801. Min Range: -1.7801

Max Act: 1.4404. Min Act: -0.0000

Data Index: 280696 (The Pile)

Max Activating Token Index: 850