Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5532 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0720. Min Act: -0.0003

Data Index: 554854 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1226754 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1327087 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0633. Min Act: -0.0002

Data Index: 208348 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0622. Min Act: -0.0002

Data Index: 755803 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0627. Min Act: -0.0002

Data Index: 410872 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0611. Min Act: -0.0002

Data Index: 593805 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0597. Min Act: -0.0002

Data Index: 82996 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0595. Min Act: -0.0002

Data Index: 898959 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1122099 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0610. Min Act: -0.0002

Data Index: 436208 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0608. Min Act: -0.0002

Data Index: 208736 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0607. Min Act: -0.0002

Data Index: 656727 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0610. Min Act: -0.0002

Data Index: 843183 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0610. Min Act: -0.0002

Data Index: 984860 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0601. Min Act: -0.0002

Data Index: 439712 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0588. Min Act: -0.0002

Data Index: 443574 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1034859 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0588. Min Act: -0.0002

Data Index: 31530 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1222714 (C4 (Web Text))

Max Activating Token Index: 100