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

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

Neuron 4168 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1068176 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0736. Min Act: -0.0002

Data Index: 815155 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1350464 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0644. Min Act: -0.0002

Data Index: 955218 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0611. Min Act: -0.0002

Data Index: 941841 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0588. Min Act: -0.0002

Data Index: 220801 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0566. Min Act: -0.0002

Data Index: 808984 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0602. Min Act: -0.0002

Data Index: 697707 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0584. Min Act: -0.0002

Data Index: 895947 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0577. Min Act: -0.0002

Data Index: 365473 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0548. Min Act: -0.0002

Data Index: 599503 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1142531 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0548. Min Act: -0.0002

Data Index: 260347 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0556. Min Act: -0.0002

Data Index: 671324 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0616. Min Act: -0.0002

Data Index: 637775 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1297135 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0548. Min Act: -0.0002

Data Index: 441447 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0516. Min Act: -0.0002

Data Index: 664024 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0549. Min Act: -0.0002

Data Index: 51015 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0531. Min Act: -0.0002

Data Index: 671298 (C4 (Web Text))

Max Activating Token Index: 868