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

Dataset: The Pile

Neuron 205 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: 1.5386. Min Range: -1.5386

Max Act: 1.2549. Min Act: -0.0000

Data Index: 276665 (The Pile)

Max Activating Token Index: 877

Text #1

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.4260. Min Act: -0.0000

Data Index: 522112 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1507765 (The Pile)

Max Activating Token Index: 450

Text #3

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.4050. Min Act: -0.0000

Data Index: 1177 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1087099 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.5386. Min Act: -0.0000

Data Index: 974564 (The Pile)

Max Activating Token Index: 747

Text #6

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3636. Min Act: -0.0000

Data Index: 1017437 (The Pile)

Max Activating Token Index: 706

Text #7

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2830. Min Act: -0.0000

Data Index: 649775 (The Pile)

Max Activating Token Index: 877

Text #8

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.5220. Min Act: -0.0000

Data Index: 78925 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2317. Min Act: -0.0000

Data Index: 1448292 (The Pile)

Max Activating Token Index: 431

Text #10

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.4575. Min Act: -0.0000

Data Index: 448759 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3323. Min Act: -0.0000

Data Index: 421478 (The Pile)

Max Activating Token Index: 986

Text #12

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1714. Min Act: -0.0000

Data Index: 1231969 (The Pile)

Max Activating Token Index: 932

Text #13

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2228. Min Act: -0.0000

Data Index: 1513718 (The Pile)

Max Activating Token Index: 587

Text #14

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1485532 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2078. Min Act: -0.0000

Data Index: 763203 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2602. Min Act: -0.0000

Data Index: 1991882 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3567. Min Act: -0.0000

Data Index: 105893 (The Pile)

Max Activating Token Index: 822

Text #18

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2098. Min Act: -0.0000

Data Index: 1557548 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1268. Min Act: -0.0000

Data Index: 523480 (The Pile)

Max Activating Token Index: 928