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

Dataset: The Pile

Neuron 4392 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: 1.8286. Min Range: -1.8286

Max Act: 1.8286. Min Act: -0.0000

Data Index: 53200 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.7376. Min Act: -0.0000

Data Index: 1336506 (The Pile)

Max Activating Token Index: 177

Text #2

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.3961. Min Act: -0.0000

Data Index: 1434154 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.4213. Min Act: -0.0000

Data Index: 886496 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1376906 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.3816. Min Act: -0.0000

Data Index: 968083 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.3754. Min Act: -0.0000

Data Index: 556763 (The Pile)

Max Activating Token Index: 409

Text #7

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.2479. Min Act: -0.0000

Data Index: 564727 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.3188. Min Act: -0.0000

Data Index: 654671 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.3173. Min Act: -0.0000

Data Index: 836617 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.1606. Min Act: -0.0000

Data Index: 1050210 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.3895. Min Act: -0.0000

Data Index: 129823 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.3538. Min Act: -0.0000

Data Index: 281291 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.3340. Min Act: -0.0000

Data Index: 874642 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1670127 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.2233. Min Act: -0.0000

Data Index: 1964704 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.2526. Min Act: -0.0000

Data Index: 807211 (The Pile)

Max Activating Token Index: 952

Text #17

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.3189. Min Act: -0.0000

Data Index: 65417 (The Pile)

Max Activating Token Index: 779

Text #18

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.1621. Min Act: -0.0000

Data Index: 1654399 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 1.8286. Min Range: -1.8286

Max Act: 1.1682. Min Act: -0.0000

Data Index: 594432 (The Pile)

Max Activating Token Index: 72