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

Dataset: The Pile

Neuron 1140 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: 0.2763. Min Range: -0.2763

Max Act: 0.2763. Min Act: -0.0000

Data Index: 492557 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1476282 (The Pile)

Max Activating Token Index: 195

Text #2

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1880. Min Act: -0.0000

Data Index: 341848 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2099. Min Act: -0.0000

Data Index: 226523 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1364277 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1699399 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2037. Min Act: -0.0000

Data Index: 1747901 (The Pile)

Max Activating Token Index: 188

Text #7

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.2002. Min Act: -0.0000

Data Index: 487919 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1909. Min Act: -0.0000

Data Index: 855441 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1838. Min Act: -0.0000

Data Index: 173571 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1968. Min Act: -0.0000

Data Index: 265476 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1742871 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1701. Min Act: -0.0000

Data Index: 693694 (The Pile)

Max Activating Token Index: 378

Text #13

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1338600 (The Pile)

Max Activating Token Index: 511

Text #14

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1444327 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1868. Min Act: -0.0000

Data Index: 415401 (The Pile)

Max Activating Token Index: 233

Text #16

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1459458 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1772. Min Act: -0.0000

Data Index: 525118 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1376504 (The Pile)

Max Activating Token Index: 520

Text #19

Max Range: 0.2763. Min Range: -0.2763

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1859889 (The Pile)

Max Activating Token Index: 464