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

Dataset: The Pile

Neuron 2014 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: 0.9531. Min Range: -0.9531

Max Act: 0.9531. Min Act: -0.0000

Data Index: 577299 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9395. Min Act: -0.0000

Data Index: 398059 (The Pile)

Max Activating Token Index: 879

Text #2

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9088. Min Act: -0.0000

Data Index: 762591 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8617. Min Act: -0.0000

Data Index: 527639 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1134446 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8573. Min Act: -0.0000

Data Index: 884459 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1070288 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1814995 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8882. Min Act: -0.0000

Data Index: 853013 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8604. Min Act: -0.0000

Data Index: 505034 (The Pile)

Max Activating Token Index: 845

Text #10

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1279365 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1787561 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1746962 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8378. Min Act: -0.0000

Data Index: 628177 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8376. Min Act: -0.0000

Data Index: 593747 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1544151 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7865. Min Act: -0.0000

Data Index: 183292 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1540884 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8050. Min Act: -0.0000

Data Index: 68210 (The Pile)

Max Activating Token Index: 154

Text #19

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1962366 (The Pile)

Max Activating Token Index: 224