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

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

Neuron 1737 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: 0.0691. Min Range: -0.0691

Max Act: 0.0691. Min Act: -0.0002

Data Index: 953775 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0681. Min Act: -0.0001

Data Index: 37439 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1122140 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0644. Min Act: -0.0002

Data Index: 882563 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0660. Min Act: -0.0002

Data Index: 835436 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0647. Min Act: -0.0002

Data Index: 359242 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0638. Min Act: -0.0000

Data Index: 634953 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0651. Min Act: -0.0002

Data Index: 594864 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1246950 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0635. Min Act: -0.0002

Data Index: 804801 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0613. Min Act: -0.0002

Data Index: 590687 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1196278 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0630. Min Act: -0.0002

Data Index: 142146 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0622. Min Act: -0.0002

Data Index: 800464 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0611. Min Act: -0.0002

Data Index: 940842 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0607. Min Act: -0.0002

Data Index: 971213 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0616. Min Act: -0.0001

Data Index: 458075 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1055180 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0601. Min Act: -0.0002

Data Index: 925077 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.0691. Min Range: -0.0691

Max Act: 0.0589. Min Act: -0.0002

Data Index: 542592 (C4 (Web Text))

Max Activating Token Index: 364