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

Dataset: The Pile

Neuron 1552 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0406. Min Act: -0.0000

Data Index: 688568 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0391. Min Act: -0.0000

Data Index: 26436 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1120280 (The Pile)

Max Activating Token Index: 648

Text #3

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0388. Min Act: -0.0000

Data Index: 178999 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0386. Min Act: -0.0000

Data Index: 919145 (The Pile)

Max Activating Token Index: 291

Text #5

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0383. Min Act: -0.0000

Data Index: 1310410 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1564415 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1480818 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0374. Min Act: -0.0000

Data Index: 64561 (The Pile)

Max Activating Token Index: 491

Text #9

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0369. Min Act: -0.0000

Data Index: 247335 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1725095 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0358. Min Act: -0.0000

Data Index: 1812247 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0356. Min Act: -0.0000

Data Index: 355407 (The Pile)

Max Activating Token Index: 45

Text #13

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1013210 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1634001 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1813441 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0344. Min Act: -0.0000

Data Index: 1638592 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0341. Min Act: -0.0000

Data Index: 471190 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1946295 (The Pile)

Max Activating Token Index: 351

Text #19

Max Range: 0.0406. Min Range: -0.0406

Max Act: 0.0338. Min Act: -0.0000

Data Index: 866052 (The Pile)

Max Activating Token Index: 485