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

Dataset: The Pile

Neuron 326 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8753. Min Act: -0.0000

Data Index: 98255 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.9789. Min Act: -0.0000

Data Index: 481023 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.8234. Min Act: -0.0000

Data Index: 1345349 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.7258. Min Act: -0.0000

Data Index: 1099428 (The Pile)

Max Activating Token Index: 483

Text #4

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.6660. Min Act: -0.0000

Data Index: 1546490 (The Pile)

Max Activating Token Index: 524

Text #5

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.6503. Min Act: -0.0000

Data Index: 1048077 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.5361. Min Act: -0.0000

Data Index: 1300813 (The Pile)

Max Activating Token Index: 951

Text #7

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.5175. Min Act: -0.0000

Data Index: 976048 (The Pile)

Max Activating Token Index: 92

Text #8

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.4832. Min Act: -0.0000

Data Index: 123737 (The Pile)

Max Activating Token Index: 528

Text #9

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.4115. Min Act: -0.0000

Data Index: 1900494 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.5278. Min Act: -0.0000

Data Index: 1889060 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.5351. Min Act: -0.0000

Data Index: 1483022 (The Pile)

Max Activating Token Index: 796

Text #12

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.3335. Min Act: -0.0000

Data Index: 1635319 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.3039. Min Act: -0.0000

Data Index: 1947493 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.4437. Min Act: -0.0000

Data Index: 1223747 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.1189. Min Act: -0.0000

Data Index: 1268648 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.4084. Min Act: -0.0000

Data Index: 202270 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.1941. Min Act: -0.0000

Data Index: 1908684 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.1139. Min Act: -0.0000

Data Index: 300212 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 3.9789. Min Range: -3.9789

Max Act: 3.1115. Min Act: -0.0000

Data Index: 1050395 (The Pile)

Max Activating Token Index: 395