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

Dataset: The Pile

Neuron 3229 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: 0.2298. Min Range: -0.2298

Max Act: 0.2298. Min Act: -0.0000

Data Index: 903130 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1949. Min Act: -0.0000

Data Index: 885749 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1546889 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1097183 (The Pile)

Max Activating Token Index: 431

Text #4

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1781916 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1043538 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1689121 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1026958 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1376672 (The Pile)

Max Activating Token Index: 255

Text #9

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1907. Min Act: -0.0000

Data Index: 750109 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1900. Min Act: -0.0000

Data Index: 498164 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1949. Min Act: -0.0000

Data Index: 905536 (The Pile)

Max Activating Token Index: 34

Text #12

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1440951 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1985815 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1785. Min Act: -0.0000

Data Index: 425028 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1719583 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1848449 (The Pile)

Max Activating Token Index: 334

Text #17

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1110947 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1740. Min Act: -0.0000

Data Index: 35742 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1730537 (The Pile)

Max Activating Token Index: 428