Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 898 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.1059. Min Act: -0.0002

Data Index: 258258 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.1039. Min Act: -0.0002

Data Index: 828354 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1229086 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1178818 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0733. Min Act: -0.0002

Data Index: 78749 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0700. Min Act: -0.0002

Data Index: 276589 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1101549 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0675. Min Act: -0.0002

Data Index: 864946 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1033004 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0684. Min Act: -0.0002

Data Index: 25133 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1034816 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0682. Min Act: -0.0002

Data Index: 557580 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1121845 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0685. Min Act: -0.0002

Data Index: 19994 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0679. Min Act: -0.0002

Data Index: 998482 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0677. Min Act: -0.0002

Data Index: 71524 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0662. Min Act: -0.0002

Data Index: 335350 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0649. Min Act: -0.0002

Data Index: 736182 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1054911 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1131275 (C4 (Web Text))

Max Activating Token Index: 259