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

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

Neuron 136 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0839. Min Act: -0.0000

Data Index: 230390 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0750. Min Act: -0.0000

Data Index: 226746 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0662. Min Act: -0.0001

Data Index: 1192875 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1338365 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0670. Min Act: -0.0000

Data Index: 673749 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0677. Min Act: -0.0000

Data Index: 1040484 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1182473 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0659. Min Act: -0.0000

Data Index: 414319 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0658. Min Act: -0.0001

Data Index: 474817 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1132888 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0639. Min Act: -0.0001

Data Index: 564668 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0617. Min Act: -0.0000

Data Index: 933989 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1195667 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0659. Min Act: -0.0000

Data Index: 911161 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0659. Min Act: -0.0000

Data Index: 503055 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1281971 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1108716 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1198221 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0616. Min Act: -0.0000

Data Index: 76960 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1335381 (C4 (Web Text))

Max Activating Token Index: 133