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

Dataset: The Pile

Neuron 473 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: 0.8901. Min Range: -0.8901

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1261691 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1704769 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.8126. Min Act: -0.0000

Data Index: 405664 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7274. Min Act: -0.0000

Data Index: 536968 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7453. Min Act: -0.0000

Data Index: 399438 (The Pile)

Max Activating Token Index: 390

Text #5

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7601. Min Act: -0.0000

Data Index: 207744 (The Pile)

Max Activating Token Index: 167

Text #6

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7287. Min Act: -0.0000

Data Index: 696167 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1170556 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7106. Min Act: -0.0000

Data Index: 757018 (The Pile)

Max Activating Token Index: 713

Text #9

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7155. Min Act: -0.0000

Data Index: 815405 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1830902 (The Pile)

Max Activating Token Index: 322

Text #11

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.7271. Min Act: -0.0000

Data Index: 647518 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6455. Min Act: -0.0000

Data Index: 744661 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6099. Min Act: -0.0000

Data Index: 644422 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1773390 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6612. Min Act: -0.0000

Data Index: 712964 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1213503 (The Pile)

Max Activating Token Index: 158

Text #17

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6535. Min Act: -0.0000

Data Index: 37508 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1598588 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 0.8901. Min Range: -0.8901

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1539876 (The Pile)

Max Activating Token Index: 31