Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1742 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0662. Min Act: -0.0002

Data Index: 701743 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1140228 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0002

Data Index: 999503 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0637. Min Act: -0.0002

Data Index: 32678 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0642. Min Act: -0.0002

Data Index: 119170 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0586. Min Act: -0.0002

Data Index: 921728 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0614. Min Act: -0.0002

Data Index: 716098 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0633. Min Act: -0.0002

Data Index: 854971 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0613. Min Act: -0.0002

Data Index: 637227 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1005635 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0622. Min Act: -0.0002

Data Index: 650185 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1006654 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1356329 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0574. Min Act: -0.0002

Data Index: 804998 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1167413 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1084472 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1219819 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1230455 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0566. Min Act: -0.0002

Data Index: 981491 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0596. Min Act: -0.0002

Data Index: 959282 (C4 (Web Text))

Max Activating Token Index: 925