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

Dataset: The Pile

Neuron 3691 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6101. Min Act: -0.0000

Data Index: 577812 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6068. Min Act: -0.0000

Data Index: 776587 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5724. Min Act: -0.0000

Data Index: 222399 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6255. Min Act: -0.0000

Data Index: 550289 (The Pile)

Max Activating Token Index: 46

Text #4

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1113778 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1377916 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5109. Min Act: -0.0001

Data Index: 352730 (The Pile)

Max Activating Token Index: 1004

Text #7

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5595. Min Act: -0.0000

Data Index: 20448 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1138020 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5621. Min Act: -0.0000

Data Index: 24806 (The Pile)

Max Activating Token Index: 33

Text #10

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1998674 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5196. Min Act: -0.0000

Data Index: 639776 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1649296 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1827103 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1616484 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1388053 (The Pile)

Max Activating Token Index: 979

Text #16

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5205. Min Act: -0.0000

Data Index: 286691 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1393468 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1340383 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5635. Min Act: -0.0000

Data Index: 188317 (The Pile)

Max Activating Token Index: 44