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

Dataset: The Pile

Neuron 1091 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1726416 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1361123 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4551. Min Act: 0.0000

Data Index: 930944 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4603. Min Act: 0.0000

Data Index: 1942693 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1791234 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4140. Min Act: 0.0001

Data Index: 62320 (The Pile)

Max Activating Token Index: 859

Text #6

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4227. Min Act: 0.0001

Data Index: 1809971 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3943. Min Act: 0.0000

Data Index: 1316475 (The Pile)

Max Activating Token Index: 94

Text #8

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4038. Min Act: 0.0000

Data Index: 462540 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4014. Min Act: 0.0000

Data Index: 797645 (The Pile)

Max Activating Token Index: 314

Text #10

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4065. Min Act: -0.0000

Data Index: 808555 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3911. Min Act: -0.0000

Data Index: 1228913 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3911. Min Act: -0.0000

Data Index: 927844 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3860. Min Act: -0.0000

Data Index: 176030 (The Pile)

Max Activating Token Index: 385

Text #14

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3848. Min Act: -0.0000

Data Index: 655370 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3683. Min Act: -0.0000

Data Index: 575418 (The Pile)

Max Activating Token Index: 291

Text #16

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3567. Min Act: -0.0000

Data Index: 246632 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1874395 (The Pile)

Max Activating Token Index: 714

Text #18

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1306746 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3708. Min Act: 0.0000

Data Index: 1249717 (The Pile)

Max Activating Token Index: 307