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

Dataset: The Pile

Neuron 3588 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0202. Min Range: -1.0202

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1704398 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.9349. Min Act: -0.0000

Data Index: 375710 (The Pile)

Max Activating Token Index: 910

Text #2

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1579631 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8751. Min Act: -0.0000

Data Index: 1120959 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1423612 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8485. Min Act: -0.0000

Data Index: 235652 (The Pile)

Max Activating Token Index: 440

Text #6

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1074851 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8153. Min Act: -0.0000

Data Index: 957516 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1846134 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1584764 (The Pile)

Max Activating Token Index: 710

Text #10

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7708. Min Act: -0.0000

Data Index: 139656 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7508. Min Act: -0.0000

Data Index: 840137 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7476. Min Act: -0.0000

Data Index: 517546 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1245210 (The Pile)

Max Activating Token Index: 605

Text #14

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1028601 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1177882 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7265. Min Act: -0.0000

Data Index: 943833 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1163544 (The Pile)

Max Activating Token Index: 863

Text #18

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.7219. Min Act: -0.0000

Data Index: 1723068 (The Pile)

Max Activating Token Index: 352

Text #19

Max Range: 1.0202. Min Range: -1.0202

Max Act: 0.6980. Min Act: -0.0000

Data Index: 164457 (The Pile)

Max Activating Token Index: 299