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

Dataset: The Pile

Neuron 3409 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.5233. Min Act: -0.0000

Data Index: 1354657 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.4755. Min Act: -0.0000

Data Index: 1438181 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.5112. Min Act: -0.0000

Data Index: 418577 (The Pile)

Max Activating Token Index: 781

Text #3

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.4280. Min Act: -0.0000

Data Index: 1659154 (The Pile)

Max Activating Token Index: 1017

Text #4

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1618301 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.1841. Min Act: -0.0000

Data Index: 474125 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.1999. Min Act: -0.0000

Data Index: 279325 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1303128 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.2415. Min Act: -0.0000

Data Index: 1064107 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.2307. Min Act: -0.0000

Data Index: 28440 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.2898. Min Act: -0.0000

Data Index: 373755 (The Pile)

Max Activating Token Index: 446

Text #11

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.2285. Min Act: -0.0000

Data Index: 1625433 (The Pile)

Max Activating Token Index: 607

Text #12

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.1912. Min Act: -0.0000

Data Index: 732049 (The Pile)

Max Activating Token Index: 535

Text #13

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.1866. Min Act: -0.0000

Data Index: 1616925 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1714130 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.1453. Min Act: -0.0000

Data Index: 1089303 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1563737 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.1184. Min Act: -0.0000

Data Index: 1259805 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1277057 (The Pile)

Max Activating Token Index: 48

Text #19

Max Range: 1.5233. Min Range: -1.5233

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1732741 (The Pile)

Max Activating Token Index: 722