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

Dataset: The Pile

Neuron 1806 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: 0.2373. Min Range: -0.2373

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1554393 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1081791 (The Pile)

Max Activating Token Index: 36

Text #2

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1832. Min Act: -0.0000

Data Index: 781618 (The Pile)

Max Activating Token Index: 321

Text #3

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1844. Min Act: -0.0000

Data Index: 269814 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1703. Min Act: -0.0000

Data Index: 986244 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1687. Min Act: -0.0000

Data Index: 615494 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1460. Min Act: -0.0000

Data Index: 232992 (The Pile)

Max Activating Token Index: 542

Text #7

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1251975 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1392. Min Act: -0.0000

Data Index: 395198 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1861573 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1446. Min Act: -0.0000

Data Index: 808648 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1360. Min Act: -0.0000

Data Index: 288487 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1306. Min Act: -0.0000

Data Index: 714583 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1464. Min Act: -0.0000

Data Index: 244257 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1319343 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1279. Min Act: -0.0000

Data Index: 88847 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1282. Min Act: -0.0000

Data Index: 709885 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1886842 (The Pile)

Max Activating Token Index: 603

Text #18

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1416. Min Act: -0.0000

Data Index: 675594 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1308. Min Act: -0.0000

Data Index: 424055 (The Pile)

Max Activating Token Index: 984