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

Dataset: The Pile

Neuron 160 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: 3.1886. Min Range: -3.1886

Max Act: 3.1886. Min Act: -0.0000

Data Index: 316 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 3.1886. Min Range: -3.1886

Max Act: 2.9248. Min Act: -0.0000

Data Index: 581134 (The Pile)

Max Activating Token Index: 266

Text #2

Max Range: 3.1886. Min Range: -3.1886

Max Act: 2.3824. Min Act: -0.0000

Data Index: 1305752 (The Pile)

Max Activating Token Index: 992

Text #3

Max Range: 3.1886. Min Range: -3.1886

Max Act: 2.7039. Min Act: -0.0000

Data Index: 351587 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 3.1886. Min Range: -3.1886

Max Act: 2.2748. Min Act: -0.0000

Data Index: 143158 (The Pile)

Max Activating Token Index: 135

Text #5

Max Range: 3.1886. Min Range: -3.1886

Max Act: 2.4844. Min Act: -0.0000

Data Index: 1548839 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.9967. Min Act: -0.0001

Data Index: 723438 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.7751. Min Act: -0.0000

Data Index: 840552 (The Pile)

Max Activating Token Index: 568

Text #8

Max Range: 3.1886. Min Range: -3.1886

Max Act: 2.0213. Min Act: -0.0000

Data Index: 1475096 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 3.1886. Min Range: -3.1886

Max Act: 2.3466. Min Act: -0.0000

Data Index: 700507 (The Pile)

Max Activating Token Index: 788

Text #10

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.8877. Min Act: -0.0000

Data Index: 1462308 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.8553. Min Act: -0.0000

Data Index: 1539602 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.9534. Min Act: -0.0000

Data Index: 1720164 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 3.1886. Min Range: -3.1886

Max Act: 2.2563. Min Act: -0.0000

Data Index: 871066 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.9155. Min Act: -0.0000

Data Index: 1983486 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.6463. Min Act: -0.0000

Data Index: 1405280 (The Pile)

Max Activating Token Index: 612

Text #16

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.7147. Min Act: -0.0000

Data Index: 1344673 (The Pile)

Max Activating Token Index: 719

Text #17

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.8225. Min Act: -0.0000

Data Index: 776556 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.8911. Min Act: -0.0000

Data Index: 1049305 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.5955. Min Act: -0.0000

Data Index: 592943 (The Pile)

Max Activating Token Index: 418