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

Dataset: The Pile

Neuron 1569 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: 0.1977. Min Range: -0.1977

Max Act: 0.1977. Min Act: -0.0000

Data Index: 36274 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1352191 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1815692 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1226705 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1690174 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1319334 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1493. Min Act: -0.0000

Data Index: 395630 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1144504 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1456. Min Act: -0.0000

Data Index: 619275 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1529. Min Act: -0.0000

Data Index: 446014 (The Pile)

Max Activating Token Index: 314

Text #10

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1447877 (The Pile)

Max Activating Token Index: 755

Text #11

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1152012 (The Pile)

Max Activating Token Index: 781

Text #12

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1211. Min Act: -0.0000

Data Index: 899591 (The Pile)

Max Activating Token Index: 715

Text #13

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1331. Min Act: -0.0000

Data Index: 397196 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1364330 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1370. Min Act: -0.0000

Data Index: 269215 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1444. Min Act: -0.0000

Data Index: 1530049 (The Pile)

Max Activating Token Index: 555

Text #17

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1247. Min Act: -0.0000

Data Index: 80509 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1263368 (The Pile)

Max Activating Token Index: 881

Text #19

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1603732 (The Pile)

Max Activating Token Index: 361