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

Dataset: The Pile

Neuron 2216 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1724. Min Act: -0.0000

Data Index: 482601 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1656. Min Act: -0.0000

Data Index: 372855 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1623. Min Act: -0.0000

Data Index: 940689 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1869. Min Act: -0.0000

Data Index: 940289 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1530. Min Act: -0.0000

Data Index: 728916 (The Pile)

Max Activating Token Index: 268

Text #5

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1491984 (The Pile)

Max Activating Token Index: 53

Text #6

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1527. Min Act: -0.0000

Data Index: 35787 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1584909 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1457. Min Act: -0.0000

Data Index: 1404534 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1041499 (The Pile)

Max Activating Token Index: 349

Text #10

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1406405 (The Pile)

Max Activating Token Index: 70

Text #11

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1016497 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1968905 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1535. Min Act: -0.0000

Data Index: 357910 (The Pile)

Max Activating Token Index: 787

Text #14

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1464. Min Act: -0.0000

Data Index: 1284570 (The Pile)

Max Activating Token Index: 877

Text #15

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1437. Min Act: -0.0000

Data Index: 315172 (The Pile)

Max Activating Token Index: 809

Text #16

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1283046 (The Pile)

Max Activating Token Index: 639

Text #17

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1405. Min Act: -0.0000

Data Index: 522589 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1573393 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1331134 (The Pile)

Max Activating Token Index: 371