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

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

Neuron 843 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0763. Min Act: -0.0005

Data Index: 639970 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0726. Min Act: -0.0005

Data Index: 1298037 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0779. Min Act: -0.0005

Data Index: 870554 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0702. Min Act: -0.0005

Data Index: 32413 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0686. Min Act: -0.0005

Data Index: 803806 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0686. Min Act: -0.0005

Data Index: 796162 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0693. Min Act: -0.0005

Data Index: 959345 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0654. Min Act: -0.0005

Data Index: 1305341 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0659. Min Act: -0.0005

Data Index: 120085 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0655. Min Act: -0.0005

Data Index: 236370 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0616. Min Act: -0.0005

Data Index: 1254660 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0659. Min Act: -0.0005

Data Index: 250044 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0623. Min Act: -0.0005

Data Index: 237221 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0671. Min Act: -0.0005

Data Index: 1220776 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0606. Min Act: -0.0005

Data Index: 213840 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0601. Min Act: -0.0005

Data Index: 289476 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0576. Min Act: -0.0005

Data Index: 166227 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0612. Min Act: -0.0005

Data Index: 1329503 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0603. Min Act: -0.0005

Data Index: 846306 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0573. Min Act: -0.0005

Data Index: 1208724 (C4 (Web Text))

Max Activating Token Index: 662