Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 809 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1156555 (The Pile)

Max Activating Token Index: 323

Text #1

Max Range: 1.0283. Min Range: -1.0283

Max Act: 1.0283. Min Act: -0.0000

Data Index: 910437 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1399167 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7439. Min Act: -0.0000

Data Index: 598104 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8971. Min Act: -0.0000

Data Index: 652384 (The Pile)

Max Activating Token Index: 507

Text #5

Max Range: 1.0283. Min Range: -1.0283

Max Act: 1.0217. Min Act: -0.0000

Data Index: 871961 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1518947 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1788456 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9220. Min Act: -0.0000

Data Index: 659231 (The Pile)

Max Activating Token Index: 850

Text #9

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8236. Min Act: -0.0000

Data Index: 80235 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9008. Min Act: -0.0000

Data Index: 276638 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1434423 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.5257. Min Act: -0.0000

Data Index: 376134 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1414815 (The Pile)

Max Activating Token Index: 823

Text #14

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8440. Min Act: -0.0000

Data Index: 394520 (The Pile)

Max Activating Token Index: 636

Text #15

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.8113. Min Act: -0.0000

Data Index: 730901 (The Pile)

Max Activating Token Index: 236

Text #16

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7764. Min Act: -0.0000

Data Index: 512528 (The Pile)

Max Activating Token Index: 708

Text #17

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.7311. Min Act: -0.0000

Data Index: 686306 (The Pile)

Max Activating Token Index: 636

Text #18

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1603499 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 1.0283. Min Range: -1.0283

Max Act: 0.6370. Min Act: -0.0000

Data Index: 614299 (The Pile)

Max Activating Token Index: 49