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

Dataset: The Pile

Neuron 2983 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1286167 (The Pile)

Max Activating Token Index: 719

Text #1

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1038. Min Act: -0.0000

Data Index: 1616383 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1350815 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1393378 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0962. Min Act: -0.0000

Data Index: 112782 (The Pile)

Max Activating Token Index: 71

Text #5

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0931. Min Act: -0.0000

Data Index: 1330519 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1584153 (The Pile)

Max Activating Token Index: 9

Text #7

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1280795 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1140983 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1049255 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1568354 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0878. Min Act: -0.0000

Data Index: 16035 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0858. Min Act: -0.0000

Data Index: 266484 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1646732 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1875427 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0843. Min Act: -0.0000

Data Index: 5139 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1607693 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0830. Min Act: -0.0000

Data Index: 62821 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0832. Min Act: -0.0000

Data Index: 331094 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 0.1397. Min Range: -0.1397

Max Act: 0.0860. Min Act: -0.0000

Data Index: 211517 (The Pile)

Max Activating Token Index: 290