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

Dataset: The Pile

Neuron 3392 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: 0.7103. Min Range: -0.7103

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1215416 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1412761 (The Pile)

Max Activating Token Index: 520

Text #2

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1129224 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1820840 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1266795 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.5106. Min Act: -0.0000

Data Index: 515916 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1054741 (The Pile)

Max Activating Token Index: 472

Text #7

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1635661 (The Pile)

Max Activating Token Index: 389

Text #8

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1780744 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1515521 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1281251 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1475439 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4492. Min Act: -0.0000

Data Index: 838894 (The Pile)

Max Activating Token Index: 481

Text #13

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4306. Min Act: -0.0000

Data Index: 972124 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1259629 (The Pile)

Max Activating Token Index: 312

Text #15

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1176798 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1239418 (The Pile)

Max Activating Token Index: 550

Text #17

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4249. Min Act: -0.0000

Data Index: 1657797 (The Pile)

Max Activating Token Index: 632

Text #18

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1185002 (The Pile)

Max Activating Token Index: 731

Text #19

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1392351 (The Pile)

Max Activating Token Index: 529