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

Dataset: The Pile

Neuron 193 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: 1.2071. Min Range: -1.2071

Max Act: 1.2041. Min Act: -0.0000

Data Index: 811973 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1943. Min Act: -0.0000

Data Index: 846032 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1211. Min Act: -0.0000

Data Index: 217014 (The Pile)

Max Activating Token Index: 596

Text #3

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1455283 (The Pile)

Max Activating Token Index: 764

Text #4

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1045. Min Act: -0.0000

Data Index: 455505 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1103. Min Act: -0.0000

Data Index: 893571 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1292. Min Act: -0.0000

Data Index: 323931 (The Pile)

Max Activating Token Index: 90

Text #7

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1619. Min Act: -0.0000

Data Index: 872184 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1037360 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1639200 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0933. Min Act: -0.0000

Data Index: 288139 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0779. Min Act: -0.0000

Data Index: 110794 (The Pile)

Max Activating Token Index: 115

Text #12

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1397433 (The Pile)

Max Activating Token Index: 942

Text #13

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1235869 (The Pile)

Max Activating Token Index: 1006

Text #14

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0394. Min Act: -0.0000

Data Index: 1400476 (The Pile)

Max Activating Token Index: 970

Text #15

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1543. Min Act: -0.0000

Data Index: 602728 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1054. Min Act: -0.0000

Data Index: 1994908 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.1238. Min Act: -0.0000

Data Index: 494468 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0983. Min Act: -0.0000

Data Index: 1410358 (The Pile)

Max Activating Token Index: 87

Text #19

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0624. Min Act: -0.0000

Data Index: 469955 (The Pile)

Max Activating Token Index: 784