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

Dataset: The Pile

Neuron 450 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: 0.1131. Min Range: -0.1131

Max Act: 0.1131. Min Act: 0.0000

Data Index: 383828 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1025. Min Act: -0.0000

Data Index: 386855 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1006. Min Act: -0.0000

Data Index: 462049 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.1000. Min Act: -0.0000

Data Index: 533453 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0930. Min Act: 0.0000

Data Index: 1282181 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0965. Min Act: 0.0000

Data Index: 1529941 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0960. Min Act: 0.0000

Data Index: 1260525 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0958. Min Act: -0.0000

Data Index: 630404 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0977. Min Act: 0.0000

Data Index: 792641 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1995140 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1699619 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0928. Min Act: -0.0000

Data Index: 57800 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0928. Min Act: 0.0000

Data Index: 1089051 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1680790 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1487957 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0892. Min Act: 0.0000

Data Index: 365632 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1517160 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0892. Min Act: 0.0000

Data Index: 1804263 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0887. Min Act: 0.0000

Data Index: 911362 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1131. Min Range: -0.1131

Max Act: 0.0877. Min Act: -0.0000

Data Index: 1726962 (The Pile)

Max Activating Token Index: 1023