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

Dataset: The Pile

Neuron 673 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1649. Min Act: -0.0000

Data Index: 985774 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1651. Min Act: -0.0000

Data Index: 918981 (The Pile)

Max Activating Token Index: 211

Text #2

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1692372 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1652. Min Act: -0.0000

Data Index: 748708 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1529. Min Act: -0.0000

Data Index: 244319 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1641. Min Act: -0.0000

Data Index: 1876986 (The Pile)

Max Activating Token Index: 227

Text #6

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1599803 (The Pile)

Max Activating Token Index: 189

Text #7

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1805126 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1700881 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1485. Min Act: -0.0000

Data Index: 805483 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1071349 (The Pile)

Max Activating Token Index: 385

Text #11

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1426. Min Act: -0.0000

Data Index: 310029 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1415. Min Act: -0.0000

Data Index: 258404 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1399. Min Act: -0.0000

Data Index: 491257 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1395. Min Act: -0.0000

Data Index: 196115 (The Pile)

Max Activating Token Index: 330

Text #15

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1847200 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1423454 (The Pile)

Max Activating Token Index: 165

Text #17

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1389. Min Act: -0.0000

Data Index: 84804 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1320. Min Act: -0.0000

Data Index: 1764469 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1312. Min Act: -0.0000

Data Index: 747444 (The Pile)

Max Activating Token Index: 490