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

Dataset: The Pile

Neuron 3200 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: 0.8894. Min Range: -0.8894

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1617074 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1637655 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1566751 (The Pile)

Max Activating Token Index: 641

Text #3

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1626829 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1119440 (The Pile)

Max Activating Token Index: 440

Text #5

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8168. Min Act: -0.0000

Data Index: 777979 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8076. Min Act: -0.0000

Data Index: 483439 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8088. Min Act: -0.0000

Data Index: 585041 (The Pile)

Max Activating Token Index: 943

Text #8

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1913756 (The Pile)

Max Activating Token Index: 270

Text #9

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1241449 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7924. Min Act: -0.0000

Data Index: 988721 (The Pile)

Max Activating Token Index: 639

Text #11

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1306266 (The Pile)

Max Activating Token Index: 473

Text #12

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8169. Min Act: -0.0000

Data Index: 434983 (The Pile)

Max Activating Token Index: 875

Text #13

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1776271 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1256993 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1245600 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7754. Min Act: -0.0000

Data Index: 950427 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1744208 (The Pile)

Max Activating Token Index: 568

Text #18

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7302. Min Act: -0.0000

Data Index: 360695 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7524. Min Act: -0.0000

Data Index: 633299 (The Pile)

Max Activating Token Index: 194