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

Dataset: The Pile

Neuron 4178 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.5071. Min Act: -0.0001

Data Index: 1028910 (The Pile)

Max Activating Token Index: 717

Text #1

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2842. Min Act: -0.0000

Data Index: 952329 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3029. Min Act: -0.0000

Data Index: 14951 (The Pile)

Max Activating Token Index: 467

Text #3

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2678. Min Act: -0.0000

Data Index: 59423 (The Pile)

Max Activating Token Index: 68

Text #4

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1139647 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2438. Min Act: -0.0000

Data Index: 756693 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2083. Min Act: -0.0000

Data Index: 143993 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1562527 (The Pile)

Max Activating Token Index: 336

Text #8

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2082. Min Act: -0.0000

Data Index: 136959 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2071. Min Act: -0.0000

Data Index: 941099 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2092. Min Act: -0.0000

Data Index: 220460 (The Pile)

Max Activating Token Index: 413

Text #11

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1050858 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2336. Min Act: -0.0000

Data Index: 779885 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1048329 (The Pile)

Max Activating Token Index: 692

Text #14

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.1940. Min Act: -0.0000

Data Index: 966583 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1392502 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1547257 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.1620. Min Act: -0.0000

Data Index: 453286 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1326871 (The Pile)

Max Activating Token Index: 759

Text #19

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.1909. Min Act: -0.0000

Data Index: 621746 (The Pile)

Max Activating Token Index: 544