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

Dataset: The Pile

Neuron 2124 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.3690. Min Act: -0.0000

Data Index: 1122795 (The Pile)

Max Activating Token Index: 354

Text #1

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.2539. Min Act: -0.0000

Data Index: 1019746 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.2389. Min Act: -0.0000

Data Index: 1759312 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.0836. Min Act: -0.0000

Data Index: 88457 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.0440. Min Act: -0.0000

Data Index: 729673 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.0554. Min Act: -0.0000

Data Index: 877689 (The Pile)

Max Activating Token Index: 248

Text #6

Max Range: 1.3690. Min Range: -1.3690

Max Act: 0.9959. Min Act: -0.0000

Data Index: 1558857 (The Pile)

Max Activating Token Index: 212

Text #7

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.0555. Min Act: -0.0000

Data Index: 383627 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1411758 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 1.3690. Min Range: -1.3690

Max Act: 0.9146. Min Act: -0.0000

Data Index: 757820 (The Pile)

Max Activating Token Index: 711

Text #10

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1078381 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.0400. Min Act: -0.0000

Data Index: 398170 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 1.3690. Min Range: -1.3690

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1530708 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 1.3690. Min Range: -1.3690

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1003730 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 1.3690. Min Range: -1.3690

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1009010 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 1.3690. Min Range: -1.3690

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1665905 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1027214 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 1.3690. Min Range: -1.3690

Max Act: 0.9306. Min Act: -0.0000

Data Index: 526638 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 1.3690. Min Range: -1.3690

Max Act: 0.8740. Min Act: -0.0000

Data Index: 359906 (The Pile)

Max Activating Token Index: 266

Text #19

Max Range: 1.3690. Min Range: -1.3690

Max Act: 1.0942. Min Act: -0.0000

Data Index: 420494 (The Pile)

Max Activating Token Index: 590