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

Dataset: The Pile

Neuron 2184 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: 0.7900. Min Range: -0.7900

Max Act: 0.7900. Min Act: -0.0000

Data Index: 787719 (The Pile)

Max Activating Token Index: 828

Text #1

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1664307 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6045. Min Act: -0.0000

Data Index: 359609 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1529870 (The Pile)

Max Activating Token Index: 565

Text #4

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.6155. Min Act: -0.0000

Data Index: 566730 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5927. Min Act: -0.0000

Data Index: 763490 (The Pile)

Max Activating Token Index: 976

Text #6

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1805590 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5554. Min Act: -0.0000

Data Index: 208926 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5669. Min Act: -0.0000

Data Index: 559103 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5919. Min Act: -0.0000

Data Index: 811196 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5444. Min Act: -0.0000

Data Index: 615561 (The Pile)

Max Activating Token Index: 372

Text #11

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1529281 (The Pile)

Max Activating Token Index: 778

Text #12

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1885276 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1586838 (The Pile)

Max Activating Token Index: 61

Text #14

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5839. Min Act: -0.0000

Data Index: 703605 (The Pile)

Max Activating Token Index: 973

Text #15

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5320. Min Act: -0.0000

Data Index: 270051 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5444. Min Act: -0.0000

Data Index: 724944 (The Pile)

Max Activating Token Index: 77

Text #17

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5513. Min Act: -0.0000

Data Index: 936581 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5805. Min Act: -0.0000

Data Index: 501071 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 0.7900. Min Range: -0.7900

Max Act: 0.5453. Min Act: -0.0000

Data Index: 942485 (The Pile)

Max Activating Token Index: 319