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

Dataset: The Pile

Neuron 3391 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: 0.7581. Min Range: -0.7581

Max Act: 0.7191. Min Act: -0.0000

Data Index: 509468 (The Pile)

Max Activating Token Index: 285

Text #1

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1958369 (The Pile)

Max Activating Token Index: 515

Text #2

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.7091. Min Act: -0.0000

Data Index: 1215017 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1227160 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1430497 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1265871 (The Pile)

Max Activating Token Index: 622

Text #6

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.7145. Min Act: -0.0000

Data Index: 950039 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6675. Min Act: -0.0000

Data Index: 51401 (The Pile)

Max Activating Token Index: 839

Text #8

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1308668 (The Pile)

Max Activating Token Index: 139

Text #9

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6873. Min Act: -0.0000

Data Index: 854775 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6859. Min Act: -0.0000

Data Index: 894250 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6268. Min Act: -0.0000

Data Index: 31267 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6585. Min Act: -0.0000

Data Index: 719387 (The Pile)

Max Activating Token Index: 459

Text #13

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1037419 (The Pile)

Max Activating Token Index: 711

Text #14

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6544. Min Act: -0.0000

Data Index: 248907 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6434. Min Act: -0.0000

Data Index: 118045 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5793. Min Act: -0.0000

Data Index: 530167 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1272629 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1464690 (The Pile)

Max Activating Token Index: 790

Text #19

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1847101 (The Pile)

Max Activating Token Index: 899