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

Dataset: The Pile

Neuron 534 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: 4.1966. Min Range: -4.1966

Max Act: 4.1966. Min Act: -0.0000

Data Index: 1485822 (The Pile)

Max Activating Token Index: 346

Text #1

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.3217. Min Act: -0.0000

Data Index: 59795 (The Pile)

Max Activating Token Index: 691

Text #2

Max Range: 4.1966. Min Range: -4.1966

Max Act: 2.4220. Min Act: -0.0000

Data Index: 1714149 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.8709. Min Act: -0.0000

Data Index: 300385 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 4.1966. Min Range: -4.1966

Max Act: 2.2749. Min Act: -0.0000

Data Index: 107542 (The Pile)

Max Activating Token Index: 40

Text #5

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.8373. Min Act: -0.0000

Data Index: 1471238 (The Pile)

Max Activating Token Index: 305

Text #6

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.8751. Min Act: -0.0000

Data Index: 1866451 (The Pile)

Max Activating Token Index: 259

Text #7

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.6342. Min Act: -0.0000

Data Index: 1827120 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.6003. Min Act: -0.0000

Data Index: 1839413 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.7132. Min Act: -0.0000

Data Index: 275698 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.6718. Min Act: -0.0000

Data Index: 479520 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1265732 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.3412. Min Act: -0.0000

Data Index: 603093 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.1682. Min Act: -0.0000

Data Index: 100507 (The Pile)

Max Activating Token Index: 747

Text #14

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.6619. Min Act: -0.0000

Data Index: 547000 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.5178. Min Act: -0.0000

Data Index: 1914101 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.7650. Min Act: -0.0000

Data Index: 1927080 (The Pile)

Max Activating Token Index: 614

Text #17

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.5340. Min Act: -0.0000

Data Index: 1544262 (The Pile)

Max Activating Token Index: 325

Text #18

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.2724. Min Act: -0.0000

Data Index: 1354265 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 4.1966. Min Range: -4.1966

Max Act: 1.4093. Min Act: -0.0000

Data Index: 268072 (The Pile)

Max Activating Token Index: 984