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

Dataset: The Pile

Neuron 973 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: 0.2630. Min Range: -0.2630

Max Act: 0.2630. Min Act: -0.0000

Data Index: 828067 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1195719 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2433. Min Act: -0.0000

Data Index: 512181 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2308. Min Act: -0.0000

Data Index: 531003 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1272564 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2038. Min Act: -0.0000

Data Index: 75233 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1213359 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1621. Min Act: -0.0000

Data Index: 565055 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2165. Min Act: -0.0000

Data Index: 282026 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1032888 (The Pile)

Max Activating Token Index: 596

Text #10

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1875464 (The Pile)

Max Activating Token Index: 289

Text #11

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1712112 (The Pile)

Max Activating Token Index: 750

Text #12

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1617798 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1788. Min Act: -0.0000

Data Index: 870269 (The Pile)

Max Activating Token Index: 681

Text #14

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1384685 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2010. Min Act: -0.0000

Data Index: 649517 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1351321 (The Pile)

Max Activating Token Index: 455

Text #17

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1545004 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1142131 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1819. Min Act: -0.0000

Data Index: 109326 (The Pile)

Max Activating Token Index: 891