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

Dataset: The Pile

Neuron 4982 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: 0.2545. Min Range: -0.2545

Max Act: 0.2545. Min Act: -0.0000

Data Index: 592633 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1697. Min Act: -0.0000

Data Index: 552489 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1089270 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1188160 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1603. Min Act: -0.0000

Data Index: 807271 (The Pile)

Max Activating Token Index: 493

Text #5

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1529. Min Act: -0.0000

Data Index: 963624 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1283494 (The Pile)

Max Activating Token Index: 914

Text #7

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1436. Min Act: -0.0000

Data Index: 961561 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1446. Min Act: -0.0000

Data Index: 1404175 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1933624 (The Pile)

Max Activating Token Index: 775

Text #10

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1409006 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1303. Min Act: -0.0000

Data Index: 893133 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1683952 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1273. Min Act: -0.0000

Data Index: 925744 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1228. Min Act: -0.0000

Data Index: 645964 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1884458 (The Pile)

Max Activating Token Index: 383

Text #16

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1307575 (The Pile)

Max Activating Token Index: 631

Text #17

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1653244 (The Pile)

Max Activating Token Index: 306

Text #18

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1214. Min Act: -0.0000

Data Index: 510102 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 0.2545. Min Range: -0.2545

Max Act: 0.1186. Min Act: -0.0000

Data Index: 716408 (The Pile)

Max Activating Token Index: 930