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

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

Neuron 3434 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1237223 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0705. Min Act: -0.0002

Data Index: 857088 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0650. Min Act: -0.0002

Data Index: 61349 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0634. Min Act: -0.0002

Data Index: 735729 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1581147 (Python Code)

Max Activating Token Index: 135

Text #5

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0590. Min Act: -0.0002

Data Index: 108396 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0591. Min Act: -0.0002

Data Index: 961247 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0581. Min Act: -0.0002

Data Index: 286009 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0580. Min Act: -0.0002

Data Index: 940943 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1057617 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1239068 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0566. Min Act: -0.0002

Data Index: 476118 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0564. Min Act: -0.0002

Data Index: 844097 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1029160 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1147935 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1352194 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0556. Min Act: -0.0002

Data Index: 326452 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0554. Min Act: -0.0002

Data Index: 700135 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0552. Min Act: -0.0002

Data Index: 663426 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0551. Min Act: -0.0002

Data Index: 58672 (C4 (Web Text))

Max Activating Token Index: 394