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

Dataset: The Pile

Neuron 5090 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: 0.9899. Min Range: -0.9899

Max Act: 0.9899. Min Act: -0.0000

Data Index: 119904 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1799037 (The Pile)

Max Activating Token Index: 666

Text #2

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9305. Min Act: -0.0000

Data Index: 53851 (The Pile)

Max Activating Token Index: 767

Text #3

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1773895 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1917656 (The Pile)

Max Activating Token Index: 274

Text #5

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7839. Min Act: -0.0000

Data Index: 552230 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7797. Min Act: -0.0000

Data Index: 699166 (The Pile)

Max Activating Token Index: 870

Text #7

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7633. Min Act: -0.0000

Data Index: 708065 (The Pile)

Max Activating Token Index: 464

Text #8

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7377. Min Act: -0.0000

Data Index: 67306 (The Pile)

Max Activating Token Index: 491

Text #9

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7557. Min Act: -0.0000

Data Index: 489772 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1083823 (The Pile)

Max Activating Token Index: 438

Text #11

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.6792. Min Act: -0.0000

Data Index: 190335 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.6710. Min Act: -0.0000

Data Index: 301055 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.6734. Min Act: -0.0000

Data Index: 591902 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1884643 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1969403 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.6393. Min Act: -0.0000

Data Index: 18174 (The Pile)

Max Activating Token Index: 824

Text #17

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1210004 (The Pile)

Max Activating Token Index: 149

Text #18

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.6233. Min Act: -0.0000

Data Index: 236444 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1292487 (The Pile)

Max Activating Token Index: 390