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

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

Neuron 3960 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1278895 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0778. Min Act: -0.0001

Data Index: 11987 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0820. Min Act: -0.0001

Data Index: 57850 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0778. Min Act: -0.0001

Data Index: 844208 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0705. Min Act: -0.0001

Data Index: 291999 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1064721 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0702. Min Act: -0.0001

Data Index: 456244 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0645. Min Act: -0.0001

Data Index: 239571 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0686. Min Act: -0.0001

Data Index: 916931 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0680. Min Act: -0.0001

Data Index: 540515 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0591. Min Act: -0.0001

Data Index: 19716 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0617. Min Act: -0.0001

Data Index: 3134 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0619. Min Act: -0.0001

Data Index: 765562 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1331789 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0574. Min Act: -0.0001

Data Index: 423988 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1284485 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1298143 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0635. Min Act: -0.0001

Data Index: 117947 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0608. Min Act: -0.0001

Data Index: 712201 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.0820. Min Range: -0.0820

Max Act: 0.0656. Min Act: -0.0001

Data Index: 10944 (C4 (Web Text))

Max Activating Token Index: 740