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

Dataset: The Pile

Neuron 2022 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: 2.1749. Min Range: -2.1749

Max Act: 2.1749. Min Act: -0.0000

Data Index: 194483 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 2.1749. Min Range: -2.1749

Max Act: 2.0879. Min Act: -0.0000

Data Index: 1498000 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.9474. Min Act: -0.0000

Data Index: 1069968 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.9434. Min Act: -0.0000

Data Index: 865763 (The Pile)

Max Activating Token Index: 755

Text #4

Max Range: 2.1749. Min Range: -2.1749

Max Act: 2.0574. Min Act: -0.0000

Data Index: 685916 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 2.1749. Min Range: -2.1749

Max Act: 2.0106. Min Act: -0.0000

Data Index: 880483 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 2.1749. Min Range: -2.1749

Max Act: 2.1619. Min Act: -0.0000

Data Index: 709901 (The Pile)

Max Activating Token Index: 747

Text #7

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.9637. Min Act: -0.0000

Data Index: 1000010 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.9711. Min Act: -0.0000

Data Index: 1942593 (The Pile)

Max Activating Token Index: 854

Text #9

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.9324. Min Act: -0.0000

Data Index: 1855228 (The Pile)

Max Activating Token Index: 99

Text #10

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.9406. Min Act: -0.0000

Data Index: 445015 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.9222. Min Act: -0.0000

Data Index: 1920284 (The Pile)

Max Activating Token Index: 314

Text #12

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.8233. Min Act: -0.0000

Data Index: 1300247 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.9397. Min Act: -0.0000

Data Index: 1923336 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.9947. Min Act: -0.0000

Data Index: 798798 (The Pile)

Max Activating Token Index: 463

Text #15

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.8788. Min Act: -0.0000

Data Index: 776266 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.8344. Min Act: -0.0000

Data Index: 11308 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.9525. Min Act: -0.0000

Data Index: 1690456 (The Pile)

Max Activating Token Index: 352

Text #18

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.8286. Min Act: -0.0000

Data Index: 332987 (The Pile)

Max Activating Token Index: 9

Text #19

Max Range: 2.1749. Min Range: -2.1749

Max Act: 1.7870. Min Act: -0.0000

Data Index: 90847 (The Pile)

Max Activating Token Index: 580