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

Dataset: The Pile

Neuron 4035 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 946973 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 282348 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 582468 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 473369 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 710753 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1847621 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 266241 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1293225 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1541955 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1397171 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 880768 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1238917 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 126761 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1052213 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1064156 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0003

Data Index: 1070381 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1207116 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0003

Data Index: 1712938 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 228027 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0003

Data Index: 828763 (The Pile)

Max Activating Token Index: 231