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

Dataset: The Pile

Neuron 1178 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8894. Min Act: -0.0000

Data Index: 564959 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1511706 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8248. Min Act: -0.0000

Data Index: 954835 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.8263. Min Act: -0.0000

Data Index: 977381 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1565991 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1901615 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7390. Min Act: -0.0000

Data Index: 818875 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7543. Min Act: -0.0000

Data Index: 796759 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7661. Min Act: -0.0000

Data Index: 917186 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1591554 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7304. Min Act: -0.0000

Data Index: 320875 (The Pile)

Max Activating Token Index: 300

Text #11

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6960. Min Act: -0.0000

Data Index: 598853 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6985. Min Act: -0.0000

Data Index: 220223 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1158421 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1238572 (The Pile)

Max Activating Token Index: 144

Text #15

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1315469 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1434867 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.6608. Min Act: -0.0000

Data Index: 554808 (The Pile)

Max Activating Token Index: 259

Text #18

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1013854 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 0.8894. Min Range: -0.8894

Max Act: 0.7501. Min Act: -0.0000

Data Index: 902623 (The Pile)

Max Activating Token Index: 977