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

Dataset: The Pile

Neuron 2917 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0676. Min Act: 0.0000

Data Index: 1752669 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0699. Min Act: 0.0000

Data Index: 1509084 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0623. Min Act: 0.0000

Data Index: 1297064 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0617. Min Act: 0.0000

Data Index: 922147 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0603. Min Act: 0.0001

Data Index: 1419872 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0598. Min Act: 0.0000

Data Index: 243697 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0616. Min Act: 0.0000

Data Index: 1303111 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0594. Min Act: 0.0000

Data Index: 1241202 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0593. Min Act: 0.0000

Data Index: 1637012 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0593. Min Act: 0.0000

Data Index: 851451 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0592. Min Act: 0.0000

Data Index: 1581099 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0591. Min Act: 0.0000

Data Index: 515091 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0588. Min Act: 0.0000

Data Index: 582271 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0586. Min Act: -0.0000

Data Index: 612665 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0585. Min Act: 0.0000

Data Index: 221896 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0565. Min Act: 0.0000

Data Index: 1634144 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0606. Min Act: 0.0000

Data Index: 1555507 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0581. Min Act: 0.0000

Data Index: 323187 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0582. Min Act: 0.0000

Data Index: 1209808 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1603916 (The Pile)

Max Activating Token Index: 1023