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

Dataset: The Pile

Neuron 3234 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: 0.3239. Min Range: -0.3239

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1560415 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1792. Min Act: -0.0000

Data Index: 35883 (The Pile)

Max Activating Token Index: 426

Text #2

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1888. Min Act: -0.0000

Data Index: 449166 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1303996 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1689. Min Act: -0.0000

Data Index: 881534 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1782. Min Act: -0.0000

Data Index: 548626 (The Pile)

Max Activating Token Index: 663

Text #6

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1404246 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1507. Min Act: -0.0000

Data Index: 993015 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1474. Min Act: -0.0000

Data Index: 905522 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1190269 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1417. Min Act: -0.0000

Data Index: 991617 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1579883 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1406. Min Act: -0.0000

Data Index: 923217 (The Pile)

Max Activating Token Index: 475

Text #13

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1329609 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1444. Min Act: -0.0000

Data Index: 346178 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1009561 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1160724 (The Pile)

Max Activating Token Index: 620

Text #17

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1564. Min Act: -0.0000

Data Index: 458801 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1349. Min Act: -0.0000

Data Index: 710888 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 0.3239. Min Range: -0.3239

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1386591 (The Pile)

Max Activating Token Index: 724