Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1036 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9829. Min Act: -0.0000

Data Index: 505997 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9772. Min Act: -0.0000

Data Index: 131272 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9181. Min Act: -0.0000

Data Index: 378621 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9647. Min Act: -0.0000

Data Index: 1765641 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9081. Min Act: -0.0000

Data Index: 667545 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9448. Min Act: -0.0000

Data Index: 523890 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.8709. Min Act: -0.0000

Data Index: 221862 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1192953 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9198. Min Act: -0.0000

Data Index: 1708882 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9162. Min Act: -0.0000

Data Index: 193470 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9175. Min Act: -0.0000

Data Index: 1698839 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9154. Min Act: -0.0000

Data Index: 1325849 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9145. Min Act: -0.0000

Data Index: 1099080 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9140. Min Act: -0.0000

Data Index: 173818 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9606. Min Act: -0.0000

Data Index: 335909 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.9094. Min Act: -0.0000

Data Index: 734336 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.8554. Min Act: -0.0000

Data Index: 1899164 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.8304. Min Act: -0.0000

Data Index: 773865 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.8795. Min Act: -0.0000

Data Index: 151444 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 1.9829. Min Range: -1.9829

Max Act: 1.8775. Min Act: -0.0000

Data Index: 637982 (The Pile)

Max Activating Token Index: 1023