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

Dataset: The Pile

Neuron 422 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: 3.5430. Min Range: -3.5430

Max Act: 3.5430. Min Act: -0.0000

Data Index: 1120378 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.0561. Min Act: -0.0000

Data Index: 1756976 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.4256. Min Act: -0.0000

Data Index: 1888047 (The Pile)

Max Activating Token Index: 468

Text #3

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.0970. Min Act: -0.0000

Data Index: 1931237 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.0344. Min Act: -0.0000

Data Index: 82611 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.1639. Min Act: -0.0000

Data Index: 1178856 (The Pile)

Max Activating Token Index: 252

Text #6

Max Range: 3.5430. Min Range: -3.5430

Max Act: 2.8812. Min Act: -0.0000

Data Index: 922249 (The Pile)

Max Activating Token Index: 415

Text #7

Max Range: 3.5430. Min Range: -3.5430

Max Act: 2.9699. Min Act: -0.0000

Data Index: 1982887 (The Pile)

Max Activating Token Index: 191

Text #8

Max Range: 3.5430. Min Range: -3.5430

Max Act: 2.9104. Min Act: -0.0000

Data Index: 1191031 (The Pile)

Max Activating Token Index: 220

Text #9

Max Range: 3.5430. Min Range: -3.5430

Max Act: 2.9152. Min Act: -0.0000

Data Index: 655789 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.0287. Min Act: -0.0000

Data Index: 591669 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.0032. Min Act: -0.0000

Data Index: 369810 (The Pile)

Max Activating Token Index: 322

Text #12

Max Range: 3.5430. Min Range: -3.5430

Max Act: 2.7067. Min Act: -0.0000

Data Index: 1540193 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 3.5430. Min Range: -3.5430

Max Act: 3.1186. Min Act: -0.0000

Data Index: 1101415 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 3.5430. Min Range: -3.5430

Max Act: 2.7854. Min Act: -0.0000

Data Index: 1997341 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 3.5430. Min Range: -3.5430

Max Act: 2.6513. Min Act: -0.0000

Data Index: 123031 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 3.5430. Min Range: -3.5430

Max Act: 2.7931. Min Act: -0.0000

Data Index: 1819936 (The Pile)

Max Activating Token Index: 490

Text #17

Max Range: 3.5430. Min Range: -3.5430

Max Act: 2.8919. Min Act: -0.0000

Data Index: 1086625 (The Pile)

Max Activating Token Index: 888

Text #18

Max Range: 3.5430. Min Range: -3.5430

Max Act: 2.7516. Min Act: -0.0000

Data Index: 216157 (The Pile)

Max Activating Token Index: 355

Text #19

Max Range: 3.5430. Min Range: -3.5430

Max Act: 2.7190. Min Act: -0.0000

Data Index: 771663 (The Pile)

Max Activating Token Index: 933