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

Dataset: The Pile

Neuron 1473 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1378108 (The Pile)

Max Activating Token Index: 351

Text #1

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1513. Min Act: -0.0000

Data Index: 945333 (The Pile)

Max Activating Token Index: 456

Text #2

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1560. Min Act: -0.0000

Data Index: 32838 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1483512 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1425. Min Act: -0.0000

Data Index: 464363 (The Pile)

Max Activating Token Index: 270

Text #5

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1321. Min Act: -0.0000

Data Index: 23095 (The Pile)

Max Activating Token Index: 839

Text #6

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1627386 (The Pile)

Max Activating Token Index: 780

Text #7

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1290. Min Act: -0.0000

Data Index: 801964 (The Pile)

Max Activating Token Index: 882

Text #8

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1958476 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1281. Min Act: -0.0000

Data Index: 22640 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1277. Min Act: -0.0000

Data Index: 979273 (The Pile)

Max Activating Token Index: 707

Text #11

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1303. Min Act: -0.0000

Data Index: 604992 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1264. Min Act: -0.0000

Data Index: 113798 (The Pile)

Max Activating Token Index: 584

Text #13

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1246. Min Act: -0.0000

Data Index: 965227 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1420875 (The Pile)

Max Activating Token Index: 525

Text #15

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1170568 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1251713 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1510642 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1732531 (The Pile)

Max Activating Token Index: 795

Text #19

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1024483 (The Pile)

Max Activating Token Index: 347