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

Dataset: The Pile

Neuron 1847 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0890. Min Range: -1.0890

Max Act: 1.0890. Min Act: -0.0000

Data Index: 681039 (The Pile)

Max Activating Token Index: 446

Text #1

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9825. Min Act: -0.0000

Data Index: 1610085 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1928626 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 1.0890. Min Range: -1.0890

Max Act: 1.0143. Min Act: -0.0000

Data Index: 1796320 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.7854. Min Act: -0.0000

Data Index: 218260 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1170159 (The Pile)

Max Activating Token Index: 572

Text #6

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1697690 (The Pile)

Max Activating Token Index: 385

Text #7

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.7718. Min Act: -0.0000

Data Index: 256201 (The Pile)

Max Activating Token Index: 940

Text #8

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1054755 (The Pile)

Max Activating Token Index: 836

Text #9

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.7567. Min Act: -0.0000

Data Index: 867647 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.8643. Min Act: -0.0000

Data Index: 744438 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.7184. Min Act: -0.0000

Data Index: 840482 (The Pile)

Max Activating Token Index: 375

Text #12

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.6168. Min Act: -0.0000

Data Index: 993301 (The Pile)

Max Activating Token Index: 845

Text #13

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.7097. Min Act: -0.0000

Data Index: 124279 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1988919 (The Pile)

Max Activating Token Index: 811

Text #15

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1337109 (The Pile)

Max Activating Token Index: 363

Text #16

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.7091. Min Act: 0.0000

Data Index: 1030147 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.6888. Min Act: -0.0000

Data Index: 22613 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.6656. Min Act: -0.0000

Data Index: 540893 (The Pile)

Max Activating Token Index: 92

Text #19

Max Range: 1.0890. Min Range: -1.0890

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1659624 (The Pile)

Max Activating Token Index: 367