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

Dataset: The Pile

Neuron 323 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: 1.9415. Min Range: -1.9415

Max Act: 1.9292. Min Act: -0.0000

Data Index: 1545636 (The Pile)

Max Activating Token Index: 538

Text #1

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.7412. Min Act: -0.0000

Data Index: 80052 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.9415. Min Act: -0.0000

Data Index: 1412585 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.8348. Min Act: -0.0000

Data Index: 1381367 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.4508. Min Act: -0.0000

Data Index: 616647 (The Pile)

Max Activating Token Index: 688

Text #5

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.4928. Min Act: -0.0000

Data Index: 706832 (The Pile)

Max Activating Token Index: 977

Text #6

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.4572. Min Act: -0.0000

Data Index: 1818095 (The Pile)

Max Activating Token Index: 640

Text #7

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.4047. Min Act: -0.0000

Data Index: 1485783 (The Pile)

Max Activating Token Index: 386

Text #8

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.3865. Min Act: -0.0000

Data Index: 1395989 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.5387. Min Act: -0.0000

Data Index: 1995711 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1409223 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.4401. Min Act: -0.0000

Data Index: 742381 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.3861. Min Act: -0.0000

Data Index: 316526 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.3440. Min Act: -0.0000

Data Index: 978760 (The Pile)

Max Activating Token Index: 508

Text #14

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1735327 (The Pile)

Max Activating Token Index: 33

Text #15

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.2176. Min Act: -0.0000

Data Index: 829255 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.2352. Min Act: -0.0000

Data Index: 1963395 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.2171. Min Act: -0.0000

Data Index: 795433 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.2127. Min Act: -0.0000

Data Index: 742415 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 1.9415. Min Range: -1.9415

Max Act: 1.2511. Min Act: -0.0000

Data Index: 776810 (The Pile)

Max Activating Token Index: 568