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

Dataset: The Pile

Neuron 1643 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: 5.7619. Min Range: -5.7619

Max Act: 5.7619. Min Act: -0.0000

Data Index: 1228470 (The Pile)

Max Activating Token Index: 870

Text #1

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5451. Min Act: -0.0000

Data Index: 835226 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 5.7619. Min Range: -5.7619

Max Act: 4.8300. Min Act: 0.0000

Data Index: 954555 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.0333. Min Act: -0.0000

Data Index: 1620302 (The Pile)

Max Activating Token Index: 565

Text #4

Max Range: 5.7619. Min Range: -5.7619

Max Act: 4.8843. Min Act: -0.0000

Data Index: 384712 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 5.7619. Min Range: -5.7619

Max Act: 4.7191. Min Act: -0.0000

Data Index: 573926 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 5.7619. Min Range: -5.7619

Max Act: 4.2784. Min Act: -0.0000

Data Index: 1001297 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 5.7619. Min Range: -5.7619

Max Act: 4.3392. Min Act: -0.0000

Data Index: 380011 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 5.7619. Min Range: -5.7619

Max Act: 4.5262. Min Act: -0.0000

Data Index: 1214270 (The Pile)

Max Activating Token Index: 94

Text #9

Max Range: 5.7619. Min Range: -5.7619

Max Act: 3.9945. Min Act: -0.0000

Data Index: 852924 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 5.7619. Min Range: -5.7619

Max Act: 4.1919. Min Act: 0.0000

Data Index: 439662 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 5.7619. Min Range: -5.7619

Max Act: 4.4788. Min Act: -0.0000

Data Index: 1817146 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 5.7619. Min Range: -5.7619

Max Act: 4.0642. Min Act: -0.0000

Data Index: 642194 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 5.7619. Min Range: -5.7619

Max Act: 3.6612. Min Act: 0.0000

Data Index: 1458058 (The Pile)

Max Activating Token Index: 54

Text #14

Max Range: 5.7619. Min Range: -5.7619

Max Act: 3.8850. Min Act: -0.0000

Data Index: 451520 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 5.7619. Min Range: -5.7619

Max Act: 4.0157. Min Act: -0.0000

Data Index: 1257293 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 5.7619. Min Range: -5.7619

Max Act: 3.5974. Min Act: -0.0000

Data Index: 428863 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 5.7619. Min Range: -5.7619

Max Act: 3.3396. Min Act: -0.0000

Data Index: 200958 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 5.7619. Min Range: -5.7619

Max Act: 3.2586. Min Act: -0.0000

Data Index: 156206 (The Pile)

Max Activating Token Index: 461

Text #19

Max Range: 5.7619. Min Range: -5.7619

Max Act: 3.6190. Min Act: -0.0000

Data Index: 243575 (The Pile)

Max Activating Token Index: 301