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

Dataset: The Pile

Neuron 2523 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0116. Min Act: -0.0001

Data Index: 664093 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0108. Min Act: -0.0000

Data Index: 1069268 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0108. Min Act: -0.0000

Data Index: 1966150 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0108. Min Act: -0.0000

Data Index: 925367 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0108. Min Act: -0.0001

Data Index: 252713 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0107. Min Act: -0.0000

Data Index: 360677 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0103. Min Act: -0.0000

Data Index: 1723655 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0107. Min Act: -0.0000

Data Index: 1847761 (The Pile)

Max Activating Token Index: 979

Text #8

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0107. Min Act: -0.0001

Data Index: 1100660 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0000

Data Index: 26259 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0000

Data Index: 1035200 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0106. Min Act: -0.0000

Data Index: 1048363 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0105. Min Act: -0.0000

Data Index: 1736459 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0105. Min Act: -0.0000

Data Index: 47144 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0105. Min Act: -0.0000

Data Index: 393645 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0000

Data Index: 240492 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0000

Data Index: 816112 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0000

Data Index: 1864441 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0000

Data Index: 180435 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0116. Min Range: -0.0116

Max Act: 0.0104. Min Act: -0.0000

Data Index: 38635 (The Pile)

Max Activating Token Index: 968