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

Dataset: The Pile

Neuron 5091 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1911. Min Range: -1.1911

Max Act: 1.1778. Min Act: -0.0000

Data Index: 1317335 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 1.1911. Min Range: -1.1911

Max Act: 1.1911. Min Act: -0.0000

Data Index: 26855 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 1.1911. Min Range: -1.1911

Max Act: 1.1062. Min Act: -0.0000

Data Index: 749540 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 1.1911. Min Range: -1.1911

Max Act: 1.1696. Min Act: 0.0000

Data Index: 634674 (The Pile)

Max Activating Token Index: 255

Text #4

Max Range: 1.1911. Min Range: -1.1911

Max Act: 1.0031. Min Act: 0.0001

Data Index: 1781036 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 1.1911. Min Range: -1.1911

Max Act: 1.0283. Min Act: -0.0000

Data Index: 301481 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1020812 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.9645. Min Act: -0.0000

Data Index: 353317 (The Pile)

Max Activating Token Index: 865

Text #8

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.9513. Min Act: 0.0001

Data Index: 877519 (The Pile)

Max Activating Token Index: 217

Text #9

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1868798 (The Pile)

Max Activating Token Index: 460

Text #10

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.8611. Min Act: -0.0000

Data Index: 430210 (The Pile)

Max Activating Token Index: 688

Text #11

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1234348 (The Pile)

Max Activating Token Index: 130

Text #12

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.8992. Min Act: -0.0000

Data Index: 1469049 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.8806. Min Act: -0.0000

Data Index: 424634 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.7999. Min Act: -0.0000

Data Index: 762496 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.8006. Min Act: -0.0000

Data Index: 807300 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1330560 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.8234. Min Act: -0.0000

Data Index: 475287 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1653201 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 1.1911. Min Range: -1.1911

Max Act: 0.7208. Min Act: -0.0000

Data Index: 62427 (The Pile)

Max Activating Token Index: 428