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

Dataset: The Pile

Neuron 927 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: 0.2471. Min Range: -0.2471

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1545829 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.2039. Min Act: -0.0000

Data Index: 652652 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1894249 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1899341 (The Pile)

Max Activating Token Index: 743

Text #4

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1193017 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1911741 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1121086 (The Pile)

Max Activating Token Index: 834

Text #7

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1513. Min Act: -0.0000

Data Index: 317158 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1530548 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1508. Min Act: -0.0000

Data Index: 378561 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1298113 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1022686 (The Pile)

Max Activating Token Index: 663

Text #12

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1499. Min Act: -0.0000

Data Index: 278006 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1310. Min Act: -0.0000

Data Index: 687337 (The Pile)

Max Activating Token Index: 941

Text #14

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1221738 (The Pile)

Max Activating Token Index: 101

Text #15

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1989178 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1282. Min Act: -0.0000

Data Index: 374085 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1421. Min Act: -0.0000

Data Index: 773651 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1014206 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 0.2471. Min Range: -0.2471

Max Act: 0.1547. Min Act: -0.0000

Data Index: 740779 (The Pile)

Max Activating Token Index: 966