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

Dataset: The Pile

Neuron 3451 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.2817. Min Act: -0.0000

Data Index: 671008 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.3867. Min Act: -0.0000

Data Index: 1927199 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1186214 (The Pile)

Max Activating Token Index: 560

Text #3

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1457. Min Act: -0.0000

Data Index: 907660 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.2478. Min Act: -0.0000

Data Index: 1351038 (The Pile)

Max Activating Token Index: 127

Text #5

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1445. Min Act: -0.0000

Data Index: 610975 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1599574 (The Pile)

Max Activating Token Index: 783

Text #7

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1977430 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1039. Min Act: -0.0000

Data Index: 1621518 (The Pile)

Max Activating Token Index: 800

Text #9

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0605. Min Act: -0.0000

Data Index: 684757 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1206. Min Act: -0.0000

Data Index: 1582570 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1934516 (The Pile)

Max Activating Token Index: 126

Text #12

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.9948. Min Act: -0.0000

Data Index: 1794978 (The Pile)

Max Activating Token Index: 1001

Text #13

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0831. Min Act: -0.0000

Data Index: 471275 (The Pile)

Max Activating Token Index: 289

Text #14

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1460. Min Act: -0.0000

Data Index: 1667328 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1582. Min Act: -0.0000

Data Index: 550840 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.0233. Min Act: -0.0000

Data Index: 1317312 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1138020 (The Pile)

Max Activating Token Index: 310

Text #18

Max Range: 1.3867. Min Range: -1.3867

Max Act: 0.9908. Min Act: -0.0000

Data Index: 1564959 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 1.3867. Min Range: -1.3867

Max Act: 1.1486. Min Act: -0.0000

Data Index: 989837 (The Pile)

Max Activating Token Index: 262