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

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

Neuron 1857 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: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0003

Data Index: 647456 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0703. Min Act: -0.0003

Data Index: 550627 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1079815 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1181002 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1219018 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1345713 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0698. Min Act: -0.0002

Data Index: 704547 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1036999 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0680. Min Act: -0.0003

Data Index: 1237449 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0669. Min Act: -0.0004

Data Index: 239360 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0672. Min Act: -0.0003

Data Index: 747775 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1058438 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0648. Min Act: -0.0004

Data Index: 374731 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0646. Min Act: -0.0003

Data Index: 726361 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0663. Min Act: -0.0003

Data Index: 183234 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0636. Min Act: -0.0003

Data Index: 463233 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0626. Min Act: -0.0003

Data Index: 766669 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0638. Min Act: -0.0002

Data Index: 161129 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1078681 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0644. Min Act: -0.0003

Data Index: 668940 (C4 (Web Text))

Max Activating Token Index: 51