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

Dataset: The Pile

Neuron 1030 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: 5.0355. Min Range: -5.0355

Max Act: 4.8947. Min Act: -0.0000

Data Index: 1923399 (The Pile)

Max Activating Token Index: 873

Text #1

Max Range: 5.0355. Min Range: -5.0355

Max Act: 5.0355. Min Act: -0.0000

Data Index: 1744514 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 5.0355. Min Range: -5.0355

Max Act: 4.1337. Min Act: -0.0000

Data Index: 1834429 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.8921. Min Act: -0.0000

Data Index: 1191728 (The Pile)

Max Activating Token Index: 893

Text #4

Max Range: 5.0355. Min Range: -5.0355

Max Act: 4.3215. Min Act: -0.0000

Data Index: 1862859 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.9168. Min Act: -0.0000

Data Index: 46815 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.7387. Min Act: -0.0000

Data Index: 856818 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.3376. Min Act: -0.0000

Data Index: 586762 (The Pile)

Max Activating Token Index: 770

Text #8

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.3379. Min Act: -0.0000

Data Index: 707166 (The Pile)

Max Activating Token Index: 980

Text #9

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.6057. Min Act: -0.0000

Data Index: 778862 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.8497. Min Act: -0.0000

Data Index: 1867180 (The Pile)

Max Activating Token Index: 805

Text #11

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.1911. Min Act: -0.0000

Data Index: 575698 (The Pile)

Max Activating Token Index: 987

Text #12

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.3692. Min Act: -0.0000

Data Index: 1166611 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.1770. Min Act: -0.0000

Data Index: 78021 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.2292. Min Act: -0.0000

Data Index: 1432915 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.2127. Min Act: -0.0000

Data Index: 1439575 (The Pile)

Max Activating Token Index: 67

Text #16

Max Range: 5.0355. Min Range: -5.0355

Max Act: 2.9319. Min Act: -0.0000

Data Index: 1323374 (The Pile)

Max Activating Token Index: 642

Text #17

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.4301. Min Act: -0.0000

Data Index: 1633661 (The Pile)

Max Activating Token Index: 1015

Text #18

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.2645. Min Act: -0.0000

Data Index: 687432 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 5.0355. Min Range: -5.0355

Max Act: 3.1688. Min Act: -0.0000

Data Index: 1619203 (The Pile)

Max Activating Token Index: 791