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

Dataset: The Pile

Neuron 3388 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: 1.3548. Min Range: -1.3548

Max Act: 1.3548. Min Act: -0.0000

Data Index: 29234 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1004359 (The Pile)

Max Activating Token Index: 1015

Text #2

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.2014. Min Act: -0.0000

Data Index: 625847 (The Pile)

Max Activating Token Index: 797

Text #3

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.2256. Min Act: -0.0000

Data Index: 129847 (The Pile)

Max Activating Token Index: 708

Text #4

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1473078 (The Pile)

Max Activating Token Index: 340

Text #5

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.2800. Min Act: -0.0000

Data Index: 926481 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.2364. Min Act: -0.0000

Data Index: 322484 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1835732 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.1471. Min Act: 0.0000

Data Index: 435524 (The Pile)

Max Activating Token Index: 265

Text #9

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1379691 (The Pile)

Max Activating Token Index: 370

Text #10

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.0803. Min Act: -0.0000

Data Index: 783341 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.0868. Min Act: -0.0000

Data Index: 835971 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.1162. Min Act: -0.0000

Data Index: 1246615 (The Pile)

Max Activating Token Index: 120

Text #13

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.0190. Min Act: -0.0000

Data Index: 774510 (The Pile)

Max Activating Token Index: 983

Text #14

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.0705. Min Act: -0.0000

Data Index: 507224 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.1223. Min Act: -0.0000

Data Index: 236586 (The Pile)

Max Activating Token Index: 604

Text #16

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.0184. Min Act: -0.0000

Data Index: 1235376 (The Pile)

Max Activating Token Index: 435

Text #17

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.1417. Min Act: -0.0000

Data Index: 531353 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 1.3548. Min Range: -1.3548

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1666681 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 1.3548. Min Range: -1.3548

Max Act: 1.0058. Min Act: 0.0000

Data Index: 961187 (The Pile)

Max Activating Token Index: 833