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

Dataset: The Pile

Neuron 647 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: 1.4793. Min Range: -1.4793

Max Act: 1.4757. Min Act: -0.0000

Data Index: 1217904 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.3991. Min Act: -0.0000

Data Index: 339813 (The Pile)

Max Activating Token Index: 264

Text #2

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.2438. Min Act: -0.0000

Data Index: 1121014 (The Pile)

Max Activating Token Index: 818

Text #3

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.4793. Min Act: -0.0000

Data Index: 1088662 (The Pile)

Max Activating Token Index: 674

Text #4

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.2818. Min Act: -0.0000

Data Index: 537291 (The Pile)

Max Activating Token Index: 154

Text #5

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.3334. Min Act: -0.0000

Data Index: 716805 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.2634. Min Act: -0.0000

Data Index: 256640 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.1833. Min Act: -0.0000

Data Index: 1290821 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.3241. Min Act: -0.0000

Data Index: 1671955 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.3048. Min Act: -0.0000

Data Index: 1138367 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1359015 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.2179. Min Act: -0.0000

Data Index: 1642228 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.2075. Min Act: -0.0000

Data Index: 604488 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.2031. Min Act: -0.0000

Data Index: 1893657 (The Pile)

Max Activating Token Index: 358

Text #14

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.1859. Min Act: -0.0000

Data Index: 71550 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.1927. Min Act: -0.0000

Data Index: 1113704 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1171290 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.1683. Min Act: -0.0000

Data Index: 70441 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.1098. Min Act: -0.0000

Data Index: 1730047 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 1.4793. Min Range: -1.4793

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1709430 (The Pile)

Max Activating Token Index: 498