Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 348 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0835. Min Act: -0.0003

Data Index: 958788 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1216732 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0777. Min Act: -0.0003

Data Index: 396110 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0739. Min Act: -0.0003

Data Index: 913384 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0706. Min Act: -0.0003

Data Index: 211183 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0736. Min Act: -0.0003

Data Index: 607328 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0717. Min Act: -0.0003

Data Index: 1179539 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0657. Min Act: -0.0003

Data Index: 1122103 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0678. Min Act: -0.0003

Data Index: 651014 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0660. Min Act: -0.0004

Data Index: 757148 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0651. Min Act: -0.0003

Data Index: 509217 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0642. Min Act: -0.0003

Data Index: 117789 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0647. Min Act: -0.0003

Data Index: 21794 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0630. Min Act: -0.0003

Data Index: 430708 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1199344 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0629. Min Act: -0.0003

Data Index: 936723 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0624. Min Act: -0.0004

Data Index: 1313586 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0625. Min Act: -0.0003

Data Index: 579736 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0610. Min Act: -0.0004

Data Index: 1214113 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0589. Min Act: -0.0003

Data Index: 189581 (C4 (Web Text))

Max Activating Token Index: 173