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

Dataset: The Pile

Neuron 3437 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: 0.7283. Min Range: -0.7283

Max Act: 0.7051. Min Act: -0.0000

Data Index: 351373 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1967519 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6004. Min Act: -0.0000

Data Index: 953021 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6196. Min Act: -0.0000

Data Index: 284450 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.7283. Min Act: -0.0000

Data Index: 985335 (The Pile)

Max Activating Token Index: 31

Text #5

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6777. Min Act: -0.0000

Data Index: 444160 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1675306 (The Pile)

Max Activating Token Index: 793

Text #7

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1954282 (The Pile)

Max Activating Token Index: 89

Text #8

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1024239 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5983. Min Act: -0.0000

Data Index: 375364 (The Pile)

Max Activating Token Index: 271

Text #10

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1857494 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6494. Min Act: -0.0000

Data Index: 884350 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5581. Min Act: -0.0000

Data Index: 1365982 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1740437 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1785476 (The Pile)

Max Activating Token Index: 510

Text #15

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1659575 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1219033 (The Pile)

Max Activating Token Index: 312

Text #17

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1545751 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1660798 (The Pile)

Max Activating Token Index: 487

Text #19

Max Range: 0.7283. Min Range: -0.7283

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1445451 (The Pile)

Max Activating Token Index: 400