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

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

Neuron 1408 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.2689. Min Act: -0.0000

Data Index: 1127629 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0738. Min Act: -0.0000

Data Index: 440462 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1359657 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7471. Min Act: -0.0001

Data Index: 1196900 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7926. Min Act: -0.0000

Data Index: 783942 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7763. Min Act: -0.0000

Data Index: 534180 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.8204. Min Act: -0.0000

Data Index: 441542 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7868. Min Act: -0.0000

Data Index: 553030 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.8107. Min Act: -0.0000

Data Index: 812062 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7648. Min Act: -0.0001

Data Index: 568414 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1025572 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7833. Min Act: -0.0000

Data Index: 195670 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7938. Min Act: -0.0000

Data Index: 890880 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7373. Min Act: -0.0001

Data Index: 405603 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.6818. Min Act: -0.0000

Data Index: 801120 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7204. Min Act: -0.0000

Data Index: 7461 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7562. Min Act: -0.0001

Data Index: 218786 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.7168. Min Act: -0.0000

Data Index: 627611 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.6907. Min Act: -0.0000

Data Index: 96771 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.6962. Min Act: -0.0000

Data Index: 292631 (C4 (Web Text))

Max Activating Token Index: 551