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

Dataset: The Pile

Neuron 115 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0944. Min Act: -0.0000

Data Index: 67658 (The Pile)

Max Activating Token Index: 558

Text #1

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1859797 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1504142 (The Pile)

Max Activating Token Index: 496

Text #3

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1131462 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0975. Min Act: -0.0000

Data Index: 66491 (The Pile)

Max Activating Token Index: 222

Text #5

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1129365 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1642367 (The Pile)

Max Activating Token Index: 962

Text #7

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0888. Min Act: -0.0000

Data Index: 556232 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1382606 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0961. Min Act: -0.0000

Data Index: 416241 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0832. Min Act: -0.0000

Data Index: 881484 (The Pile)

Max Activating Token Index: 434

Text #11

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1646798 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0852. Min Act: -0.0000

Data Index: 873070 (The Pile)

Max Activating Token Index: 245

Text #13

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1218222 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1644861 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1021230 (The Pile)

Max Activating Token Index: 65

Text #16

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0901. Min Act: -0.0000

Data Index: 686398 (The Pile)

Max Activating Token Index: 419

Text #17

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0835. Min Act: -0.0000

Data Index: 1737870 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0800. Min Act: -0.0000

Data Index: 589330 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0878. Min Act: -0.0000

Data Index: 277363 (The Pile)

Max Activating Token Index: 567