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

Dataset: The Pile

Neuron 1564 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: 0.1736. Min Range: -0.1736

Max Act: 0.1633. Min Act: -0.0000

Data Index: 895368 (The Pile)

Max Activating Token Index: 237

Text #1

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1405109 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1476427 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1736. Min Act: -0.0000

Data Index: 979284 (The Pile)

Max Activating Token Index: 120

Text #4

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1323041 (The Pile)

Max Activating Token Index: 103

Text #5

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1418. Min Act: -0.0000

Data Index: 276382 (The Pile)

Max Activating Token Index: 414

Text #6

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1452. Min Act: -0.0000

Data Index: 339286 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1005673 (The Pile)

Max Activating Token Index: 494

Text #8

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1428. Min Act: -0.0000

Data Index: 14119 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1897073 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1448. Min Act: -0.0000

Data Index: 621105 (The Pile)

Max Activating Token Index: 717

Text #11

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1078712 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1443128 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1403. Min Act: -0.0000

Data Index: 88342 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1164. Min Act: -0.0000

Data Index: 955534 (The Pile)

Max Activating Token Index: 829

Text #15

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1944778 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1296. Min Act: -0.0000

Data Index: 937103 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1998594 (The Pile)

Max Activating Token Index: 772

Text #18

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1771877 (The Pile)

Max Activating Token Index: 312

Text #19

Max Range: 0.1736. Min Range: -0.1736

Max Act: 0.1201. Min Act: -0.0000

Data Index: 388377 (The Pile)

Max Activating Token Index: 277