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

Dataset: The Pile

Neuron 2665 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.2984. Min Act: -0.0000

Data Index: 1913216 (The Pile)

Max Activating Token Index: 484

Text #1

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.5606. Min Act: -0.0000

Data Index: 1676428 (The Pile)

Max Activating Token Index: 480

Text #2

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.0901. Min Act: -0.0000

Data Index: 629330 (The Pile)

Max Activating Token Index: 188

Text #3

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.2657. Min Act: -0.0000

Data Index: 1198117 (The Pile)

Max Activating Token Index: 418

Text #4

Max Range: 3.5606. Min Range: -3.5606

Max Act: 2.7919. Min Act: -0.0000

Data Index: 981872 (The Pile)

Max Activating Token Index: 592

Text #5

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.0392. Min Act: -0.0000

Data Index: 795003 (The Pile)

Max Activating Token Index: 656

Text #6

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.1315. Min Act: -0.0000

Data Index: 912074 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.1566. Min Act: -0.0000

Data Index: 1638779 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 3.5606. Min Range: -3.5606

Max Act: 2.9876. Min Act: -0.0000

Data Index: 865061 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.2867. Min Act: -0.0000

Data Index: 1066175 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 3.5606. Min Range: -3.5606

Max Act: 2.8510. Min Act: -0.0000

Data Index: 548019 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.1152. Min Act: -0.0000

Data Index: 1300257 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.2698. Min Act: -0.0000

Data Index: 952671 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.1105. Min Act: -0.0000

Data Index: 1419854 (The Pile)

Max Activating Token Index: 515

Text #14

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.0549. Min Act: -0.0000

Data Index: 212704 (The Pile)

Max Activating Token Index: 166

Text #15

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.0345. Min Act: -0.0000

Data Index: 719904 (The Pile)

Max Activating Token Index: 730

Text #16

Max Range: 3.5606. Min Range: -3.5606

Max Act: 2.8118. Min Act: -0.0000

Data Index: 975981 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 3.5606. Min Range: -3.5606

Max Act: 2.8208. Min Act: -0.0000

Data Index: 1964791 (The Pile)

Max Activating Token Index: 856

Text #18

Max Range: 3.5606. Min Range: -3.5606

Max Act: 3.1248. Min Act: -0.0000

Data Index: 1550525 (The Pile)

Max Activating Token Index: 821

Text #19

Max Range: 3.5606. Min Range: -3.5606

Max Act: 2.9406. Min Act: -0.0000

Data Index: 1382018 (The Pile)

Max Activating Token Index: 747