Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3133 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0811. Min Act: -0.0001

Data Index: 663214 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0702. Min Act: -0.0001

Data Index: 778666 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0717. Min Act: -0.0002

Data Index: 789661 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0650. Min Act: -0.0001

Data Index: 16900 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0676. Min Act: -0.0002

Data Index: 243836 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0646. Min Act: -0.0001

Data Index: 106129 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0641. Min Act: -0.0001

Data Index: 74351 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0663. Min Act: -0.0001

Data Index: 253920 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0656. Min Act: -0.0001

Data Index: 375696 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0651. Min Act: -0.0002

Data Index: 75520 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0703. Min Act: -0.0001

Data Index: 962449 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0644. Min Act: -0.0001

Data Index: 518745 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0614. Min Act: -0.0002

Data Index: 932516 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0659. Min Act: -0.0002

Data Index: 405880 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1177132 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1318454 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0619. Min Act: -0.0001

Data Index: 353677 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0561. Min Act: -0.0001

Data Index: 826137 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0591. Min Act: -0.0002

Data Index: 532108 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1096789 (C4 (Web Text))

Max Activating Token Index: 968