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

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

Neuron 4173 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1634617 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0601. Min Act: -0.0001

Data Index: 892296 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0697. Min Act: -0.0001

Data Index: 838891 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1234785 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0672. Min Act: -0.0001

Data Index: 813646 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0610. Min Act: -0.0001

Data Index: 980766 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1259658 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0649. Min Act: -0.0001

Data Index: 606615 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0642. Min Act: -0.0001

Data Index: 35300 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1199549 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0688. Min Act: -0.0001

Data Index: 444925 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1249281 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0738. Min Act: -0.0001

Data Index: 887586 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0607. Min Act: -0.0001

Data Index: 41484 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1433753 (Python Code)

Max Activating Token Index: 325

Text #15

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0524. Min Act: -0.0001

Data Index: 125309 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1161521 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1278347 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0490. Min Act: -0.0001

Data Index: 25561 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.0811. Min Range: -0.0811

Max Act: 0.0580. Min Act: -0.0001

Data Index: 412609 (C4 (Web Text))

Max Activating Token Index: 480