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

Dataset: The Pile

Neuron 1719 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: 0.1883. Min Range: -0.1883

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1561434 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1836. Min Act: -0.0000

Data Index: 894410 (The Pile)

Max Activating Token Index: 761

Text #2

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1291036 (The Pile)

Max Activating Token Index: 153

Text #3

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1883. Min Act: -0.0000

Data Index: 783963 (The Pile)

Max Activating Token Index: 658

Text #4

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1216634 (The Pile)

Max Activating Token Index: 737

Text #5

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1630572 (The Pile)

Max Activating Token Index: 313

Text #6

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1098456 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1607990 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1663368 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1569. Min Act: -0.0000

Data Index: 384698 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1669. Min Act: -0.0000

Data Index: 77282 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1605. Min Act: -0.0000

Data Index: 209116 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1608. Min Act: -0.0000

Data Index: 638583 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1492. Min Act: -0.0000

Data Index: 223343 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1472. Min Act: -0.0000

Data Index: 1942413 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1260408 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1467. Min Act: -0.0000

Data Index: 337651 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1447. Min Act: -0.0000

Data Index: 301928 (The Pile)

Max Activating Token Index: 743

Text #18

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1518670 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 0.1883. Min Range: -0.1883

Max Act: 0.1322. Min Act: -0.0000

Data Index: 570507 (The Pile)

Max Activating Token Index: 546