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

Dataset: The Pile

Neuron 1374 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: 0.1849. Min Range: -0.1849

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1570120 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1338047 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1690. Min Act: -0.0000

Data Index: 682528 (The Pile)

Max Activating Token Index: 456

Text #3

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1327764 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1580. Min Act: -0.0000

Data Index: 350433 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1613. Min Act: -0.0000

Data Index: 447557 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1447. Min Act: -0.0000

Data Index: 269717 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1102172 (The Pile)

Max Activating Token Index: 830

Text #8

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1359. Min Act: -0.0000

Data Index: 79592 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1823738 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1300. Min Act: -0.0000

Data Index: 516640 (The Pile)

Max Activating Token Index: 555

Text #11

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1439. Min Act: -0.0000

Data Index: 675800 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1122097 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1367369 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1296. Min Act: -0.0000

Data Index: 326716 (The Pile)

Max Activating Token Index: 33

Text #15

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1109882 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1323099 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1061776 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1635647 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 0.1849. Min Range: -0.1849

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1371386 (The Pile)

Max Activating Token Index: 122