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

Dataset: The Pile

Neuron 3947 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: 1.4818. Min Range: -1.4818

Max Act: 1.4818. Min Act: -0.0000

Data Index: 602051 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1288617 (The Pile)

Max Activating Token Index: 509

Text #2

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3094. Min Act: -0.0000

Data Index: 859731 (The Pile)

Max Activating Token Index: 519

Text #3

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1139943 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2256. Min Act: -0.0000

Data Index: 981078 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1636769 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2238. Min Act: -0.0000

Data Index: 1089911 (The Pile)

Max Activating Token Index: 134

Text #7

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1394. Min Act: -0.0000

Data Index: 575176 (The Pile)

Max Activating Token Index: 668

Text #8

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1382294 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2488. Min Act: -0.0000

Data Index: 1410470 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1101. Min Act: -0.0000

Data Index: 1931073 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1413. Min Act: -0.0000

Data Index: 723981 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1866. Min Act: -0.0000

Data Index: 1785069 (The Pile)

Max Activating Token Index: 138

Text #13

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1696. Min Act: -0.0000

Data Index: 709995 (The Pile)

Max Activating Token Index: 282

Text #14

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2114. Min Act: -0.0000

Data Index: 1513806 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.0303. Min Act: -0.0000

Data Index: 478705 (The Pile)

Max Activating Token Index: 158

Text #16

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1192361 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.0511. Min Act: -0.0000

Data Index: 1109466 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1151242 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1694249 (The Pile)

Max Activating Token Index: 814