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

Dataset: The Pile

Neuron 3034 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: 0.0004. Min Range: -0.0004

Max Act: 0.0004. Min Act: -0.0000

Data Index: 1336744 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0000

Data Index: 1019126 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1684892 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1023347 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0000

Data Index: 926042 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1352444 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0000

Data Index: 1126069 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0000

Data Index: 998850 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0000

Data Index: 311934 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0000

Data Index: 341225 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1302620 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0001. Min Act: -0.0000

Data Index: 804553 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0001. Min Act: -0.0000

Data Index: 930730 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1169171 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0001. Min Act: -0.0000

Data Index: 513281 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0001. Min Act: -0.0000

Data Index: 969869 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0001. Min Act: -0.0000

Data Index: 1410295 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0001. Min Act: -0.0000

Data Index: 402089 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0001. Min Act: -0.0000

Data Index: 392442 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0001. Min Act: -0.0000

Data Index: 7651 (The Pile)

Max Activating Token Index: 1023