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

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

Neuron 5425 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: 0.1035. Min Range: -0.1035

Max Act: 0.1035. Min Act: -0.0002

Data Index: 832959 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0815. Min Act: -0.0002

Data Index: 284224 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0815. Min Act: -0.0002

Data Index: 752659 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0755. Min Act: -0.0002

Data Index: 504210 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0720. Min Act: -0.0003

Data Index: 251346 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0738. Min Act: -0.0003

Data Index: 1359083 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1012551 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0675. Min Act: -0.0003

Data Index: 501850 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0672. Min Act: -0.0002

Data Index: 653615 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0643. Min Act: -0.0002

Data Index: 77781 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0642. Min Act: -0.0002

Data Index: 149511 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1041945 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0640. Min Act: -0.0002

Data Index: 97841 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0629. Min Act: -0.0002

Data Index: 62980 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0621. Min Act: -0.0002

Data Index: 520936 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0659. Min Act: -0.0002

Data Index: 646093 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0642. Min Act: -0.0002

Data Index: 824451 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1254908 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1046728 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0587. Min Act: -0.0002

Data Index: 167852 (C4 (Web Text))

Max Activating Token Index: 549