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

Dataset: The Pile

Neuron 3483 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1763. Min Act: -0.0000

Data Index: 295715 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1336066 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1656. Min Act: -0.0000

Data Index: 60237 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1867489 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1102392 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1432404 (The Pile)

Max Activating Token Index: 897

Text #6

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1281448 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1326. Min Act: -0.0000

Data Index: 624135 (The Pile)

Max Activating Token Index: 828

Text #8

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1471. Min Act: -0.0000

Data Index: 195286 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1900310 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1188696 (The Pile)

Max Activating Token Index: 915

Text #11

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1439492 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1103373 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1405. Min Act: -0.0000

Data Index: 978722 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1428840 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1940513 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1332. Min Act: -0.0000

Data Index: 124061 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1295. Min Act: -0.0000

Data Index: 1331578 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1253063 (The Pile)

Max Activating Token Index: 973

Text #19

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1322. Min Act: -0.0000

Data Index: 115433 (The Pile)

Max Activating Token Index: 724