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

Dataset: The Pile

Neuron 199 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: 1.6302. Min Range: -1.6302

Max Act: 1.6302. Min Act: -0.0000

Data Index: 1632868 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.4762. Min Act: -0.0000

Data Index: 1541804 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.1070. Min Act: -0.0000

Data Index: 188225 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.1361. Min Act: -0.0000

Data Index: 1017095 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.2432. Min Act: -0.0000

Data Index: 1728595 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.3814. Min Act: -0.0000

Data Index: 553869 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 1.6302. Min Range: -1.6302

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1061281 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1819413 (The Pile)

Max Activating Token Index: 648

Text #8

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.1973. Min Act: -0.0000

Data Index: 1888598 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.2709. Min Act: -0.0000

Data Index: 642498 (The Pile)

Max Activating Token Index: 566

Text #10

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.1359. Min Act: -0.0000

Data Index: 233921 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 1.6302. Min Range: -1.6302

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1557812 (The Pile)

Max Activating Token Index: 278

Text #12

Max Range: 1.6302. Min Range: -1.6302

Max Act: 0.9735. Min Act: -0.0000

Data Index: 1802119 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.0919. Min Act: -0.0000

Data Index: 1520747 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.0547. Min Act: -0.0000

Data Index: 1463273 (The Pile)

Max Activating Token Index: 802

Text #15

Max Range: 1.6302. Min Range: -1.6302

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1371733 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.0570. Min Act: -0.0000

Data Index: 110957 (The Pile)

Max Activating Token Index: 363

Text #17

Max Range: 1.6302. Min Range: -1.6302

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1663381 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 1.6302. Min Range: -1.6302

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1710274 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 1.6302. Min Range: -1.6302

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1096458 (The Pile)

Max Activating Token Index: 82