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

Dataset: The Pile

Neuron 1426 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: 1.2043. Min Range: -1.2043

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1845250 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.1904. Min Act: -0.0000

Data Index: 928560 (The Pile)

Max Activating Token Index: 166

Text #2

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.1512. Min Act: -0.0000

Data Index: 497826 (The Pile)

Max Activating Token Index: 302

Text #3

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9809. Min Act: -0.0000

Data Index: 1869469 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0201. Min Act: -0.0000

Data Index: 430680 (The Pile)

Max Activating Token Index: 109

Text #5

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0486. Min Act: -0.0000

Data Index: 1018343 (The Pile)

Max Activating Token Index: 491

Text #6

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9766. Min Act: -0.0000

Data Index: 671505 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.8960. Min Act: -0.0000

Data Index: 531390 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1703858 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9713. Min Act: -0.0000

Data Index: 909507 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1911822 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9876. Min Act: -0.0000

Data Index: 422945 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1256467 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 1.2043. Min Range: -1.2043

Max Act: 1.0030. Min Act: -0.0000

Data Index: 836220 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.8884. Min Act: -0.0000

Data Index: 665934 (The Pile)

Max Activating Token Index: 544

Text #15

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9116. Min Act: -0.0000

Data Index: 958755 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9277. Min Act: -0.0000

Data Index: 915999 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1131182 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.8352. Min Act: -0.0000

Data Index: 385269 (The Pile)

Max Activating Token Index: 206

Text #19

Max Range: 1.2043. Min Range: -1.2043

Max Act: 0.9446. Min Act: -0.0000

Data Index: 643526 (The Pile)

Max Activating Token Index: 143