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

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

Neuron 1952 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0767. Min Act: -0.0002

Data Index: 253467 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0736. Min Act: -0.0001

Data Index: 890223 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0670. Min Act: -0.0001

Data Index: 998214 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0669. Min Act: -0.0002

Data Index: 815335 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0669. Min Act: -0.0002

Data Index: 185080 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1170635 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0691. Min Act: -0.0002

Data Index: 161779 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1282194 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0626. Min Act: -0.0001

Data Index: 80686 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0593. Min Act: -0.0001

Data Index: 307106 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0581. Min Act: -0.0002

Data Index: 981425 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0591. Min Act: -0.0002

Data Index: 524904 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0620. Min Act: -0.0001

Data Index: 505683 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0596. Min Act: -0.0002

Data Index: 655906 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1027278 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0570. Min Act: -0.0002

Data Index: 345550 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0606. Min Act: -0.0001

Data Index: 945995 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0571. Min Act: -0.0001

Data Index: 211952 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0600. Min Act: -0.0001

Data Index: 110158 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.0767. Min Range: -0.0767

Max Act: 0.0602. Min Act: -0.0002

Data Index: 752499 (C4 (Web Text))

Max Activating Token Index: 707