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

Dataset: The Pile

Neuron 565 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: 3.1426. Min Range: -3.1426

Max Act: 3.0750. Min Act: -0.0000

Data Index: 621978 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.9243. Min Act: -0.0000

Data Index: 954189 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 3.1426. Min Range: -3.1426

Max Act: 3.1426. Min Act: -0.0000

Data Index: 683382 (The Pile)

Max Activating Token Index: 860

Text #3

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.7845. Min Act: -0.0000

Data Index: 1469760 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.5115. Min Act: -0.0000

Data Index: 311231 (The Pile)

Max Activating Token Index: 798

Text #5

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.5301. Min Act: -0.0000

Data Index: 1092971 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.6220. Min Act: -0.0000

Data Index: 1697947 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.2338. Min Act: -0.0000

Data Index: 514750 (The Pile)

Max Activating Token Index: 938

Text #8

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.4421. Min Act: -0.0000

Data Index: 844483 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.5693. Min Act: -0.0000

Data Index: 934840 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.5401. Min Act: -0.0000

Data Index: 1362631 (The Pile)

Max Activating Token Index: 696

Text #11

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.3772. Min Act: -0.0000

Data Index: 1996699 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.4955. Min Act: -0.0000

Data Index: 1335625 (The Pile)

Max Activating Token Index: 649

Text #13

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.6383. Min Act: -0.0000

Data Index: 837925 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.4178. Min Act: -0.0000

Data Index: 179989 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.2675. Min Act: -0.0000

Data Index: 1369182 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.4823. Min Act: -0.0000

Data Index: 444734 (The Pile)

Max Activating Token Index: 813

Text #17

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.1371. Min Act: -0.0000

Data Index: 131335 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.3334. Min Act: -0.0000

Data Index: 169893 (The Pile)

Max Activating Token Index: 343

Text #19

Max Range: 3.1426. Min Range: -3.1426

Max Act: 2.3394. Min Act: -0.0000

Data Index: 521243 (The Pile)

Max Activating Token Index: 584