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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1125 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8637. Min Act: -0.0001

Data Index: 231645 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8102. Min Act: -0.0001

Data Index: 255927 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7735. Min Act: -0.0001

Data Index: 1046186 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7928. Min Act: -0.0001

Data Index: 205849 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8164. Min Act: -0.0001

Data Index: 453840 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7687. Min Act: -0.0001

Data Index: 1179047 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7344. Min Act: -0.0001

Data Index: 477583 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7353. Min Act: -0.0002

Data Index: 750391 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7775. Min Act: -0.0001

Data Index: 608617 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7748. Min Act: -0.0002

Data Index: 693679 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8317. Min Act: -0.0001

Data Index: 83104 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7292. Min Act: -0.0001

Data Index: 1237577 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6858. Min Act: -0.0001

Data Index: 46916 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7034. Min Act: -0.0001

Data Index: 300475 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6692. Min Act: -0.0002

Data Index: 1257035 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7021. Min Act: -0.0002

Data Index: 951953 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6908. Min Act: -0.0001

Data Index: 857233 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7076. Min Act: -0.0002

Data Index: 377935 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6811. Min Act: -0.0002

Data Index: 1310673 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6344. Min Act: -0.0001

Data Index: 445326 (C4 (Web Text))

Max Activating Token Index: 819