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

Dataset: The Pile

Neuron 2985 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: 1.3281. Min Range: -1.3281

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1287820 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 1.3281. Min Range: -1.3281

Max Act: 1.0181. Min Act: -0.0000

Data Index: 780767 (The Pile)

Max Activating Token Index: 836

Text #2

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1235709 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.6783. Min Act: -0.0000

Data Index: 1252011 (The Pile)

Max Activating Token Index: 785

Text #4

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.7838. Min Act: -0.0000

Data Index: 1775245 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.8142. Min Act: -0.0000

Data Index: 893148 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1561897 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.7345. Min Act: -0.0000

Data Index: 969149 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.6873. Min Act: -0.0000

Data Index: 707347 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.7325. Min Act: -0.0000

Data Index: 22363 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1956660 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1792820 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.6406. Min Act: -0.0000

Data Index: 299336 (The Pile)

Max Activating Token Index: 865

Text #13

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1848241 (The Pile)

Max Activating Token Index: 771

Text #14

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1496086 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1830700 (The Pile)

Max Activating Token Index: 224

Text #16

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.6087. Min Act: -0.0000

Data Index: 923139 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.6828. Min Act: -0.0000

Data Index: 301938 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.5954. Min Act: -0.0000

Data Index: 457760 (The Pile)

Max Activating Token Index: 984

Text #19

Max Range: 1.3281. Min Range: -1.3281

Max Act: 0.6863. Min Act: -0.0000

Data Index: 446782 (The Pile)

Max Activating Token Index: 541