Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2736 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0495. Min Act: -0.0000

Data Index: 874780 (The Pile)

Max Activating Token Index: 478

Text #1

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0417. Min Act: -0.0000

Data Index: 1125429 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0432. Min Act: -0.0000

Data Index: 1941973 (The Pile)

Max Activating Token Index: 207

Text #3

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0410. Min Act: -0.0000

Data Index: 1110252 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0410. Min Act: -0.0000

Data Index: 26536 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0426. Min Act: -0.0000

Data Index: 979176 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0407. Min Act: -0.0000

Data Index: 1339694 (The Pile)

Max Activating Token Index: 930

Text #7

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0393. Min Act: -0.0001

Data Index: 76501 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0408. Min Act: -0.0000

Data Index: 1202580 (The Pile)

Max Activating Token Index: 408

Text #9

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1702543 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0400. Min Act: 0.0000

Data Index: 1490954 (The Pile)

Max Activating Token Index: 221

Text #11

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0398. Min Act: -0.0000

Data Index: 936170 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0397. Min Act: -0.0000

Data Index: 291548 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0394. Min Act: -0.0000

Data Index: 1660893 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0394. Min Act: -0.0000

Data Index: 619436 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0391. Min Act: -0.0000

Data Index: 1825806 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0390. Min Act: -0.0000

Data Index: 830138 (The Pile)

Max Activating Token Index: 306

Text #17

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0390. Min Act: -0.0000

Data Index: 662168 (The Pile)

Max Activating Token Index: 440

Text #18

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0387. Min Act: -0.0000

Data Index: 1940137 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 0.0495. Min Range: -0.0495

Max Act: 0.0395. Min Act: -0.0000

Data Index: 330982 (The Pile)

Max Activating Token Index: 304