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

Dataset: The Pile

Neuron 4393 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: 0.2856. Min Range: -0.2856

Max Act: 0.2856. Min Act: -0.0000

Data Index: 763451 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2465. Min Act: -0.0000

Data Index: 1975078 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1980482 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1395975 (The Pile)

Max Activating Token Index: 317

Text #4

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1654659 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1644. Min Act: -0.0000

Data Index: 243714 (The Pile)

Max Activating Token Index: 436

Text #6

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1524. Min Act: -0.0000

Data Index: 97399 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1233978 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1330. Min Act: -0.0000

Data Index: 653797 (The Pile)

Max Activating Token Index: 1022

Text #9

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1480. Min Act: -0.0000

Data Index: 796471 (The Pile)

Max Activating Token Index: 888

Text #10

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1308. Min Act: -0.0000

Data Index: 503946 (The Pile)

Max Activating Token Index: 474

Text #11

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1400. Min Act: -0.0000

Data Index: 373408 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1457. Min Act: -0.0000

Data Index: 687887 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1924701 (The Pile)

Max Activating Token Index: 871

Text #14

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1746589 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1375. Min Act: -0.0000

Data Index: 239399 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1384. Min Act: -0.0000

Data Index: 682171 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1624155 (The Pile)

Max Activating Token Index: 930

Text #18

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1403. Min Act: -0.0000

Data Index: 562396 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 0.2856. Min Range: -0.2856

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1174414 (The Pile)

Max Activating Token Index: 867