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

Dataset: The Pile

Neuron 2200 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: 1.5860. Min Range: -1.5860

Max Act: 1.5860. Min Act: -0.0000

Data Index: 1938490 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.3361. Min Act: -0.0000

Data Index: 722222 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.3188. Min Act: -0.0000

Data Index: 1311271 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1164000 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.3362. Min Act: -0.0000

Data Index: 1387343 (The Pile)

Max Activating Token Index: 588

Text #5

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1457159 (The Pile)

Max Activating Token Index: 704

Text #6

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.1227. Min Act: -0.0000

Data Index: 1588449 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.1208. Min Act: -0.0000

Data Index: 308185 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1381535 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.0477. Min Act: -0.0000

Data Index: 686766 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1835434 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.0102. Min Act: -0.0000

Data Index: 1138015 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.0596. Min Act: -0.0000

Data Index: 407067 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 1.5860. Min Range: -1.5860

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1832421 (The Pile)

Max Activating Token Index: 381

Text #14

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.0187. Min Act: -0.0000

Data Index: 1650216 (The Pile)

Max Activating Token Index: 398

Text #15

Max Range: 1.5860. Min Range: -1.5860

Max Act: 1.0070. Min Act: -0.0000

Data Index: 440911 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 1.5860. Min Range: -1.5860

Max Act: 0.9702. Min Act: -0.0000

Data Index: 427766 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 1.5860. Min Range: -1.5860

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1380093 (The Pile)

Max Activating Token Index: 21

Text #18

Max Range: 1.5860. Min Range: -1.5860

Max Act: 0.9844. Min Act: -0.0000

Data Index: 823434 (The Pile)

Max Activating Token Index: 528

Text #19

Max Range: 1.5860. Min Range: -1.5860

Max Act: 0.9621. Min Act: -0.0000

Data Index: 514218 (The Pile)

Max Activating Token Index: 771