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

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

Neuron 5865 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.5652. Min Act: -0.0000

Data Index: 1108800 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.3928. Min Act: -0.0000

Data Index: 365508 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.3808. Min Act: -0.0000

Data Index: 905855 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.2313. Min Act: -0.0000

Data Index: 874769 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.0846. Min Act: -0.0000

Data Index: 293604 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.1825. Min Act: 0.0000

Data Index: 1346938 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.1012. Min Act: -0.0000

Data Index: 316055 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.1019. Min Act: -0.0000

Data Index: 861526 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.1059. Min Act: -0.0000

Data Index: 478740 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.0421. Min Act: -0.0000

Data Index: 201440 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.0412. Min Act: 0.0000

Data Index: 294874 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1232574 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.0136. Min Act: -0.0000

Data Index: 857584 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.5652. Min Range: -1.5652

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1224843 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.5652. Min Range: -1.5652

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1083064 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 1.5652. Min Range: -1.5652

Max Act: 0.9717. Min Act: -0.0000

Data Index: 794016 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.5652. Min Range: -1.5652

Max Act: 0.8992. Min Act: -0.0000

Data Index: 324848 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 1.5652. Min Range: -1.5652

Max Act: 0.8890. Min Act: -0.0000

Data Index: 813798 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 1.5652. Min Range: -1.5652

Max Act: 0.9798. Min Act: 0.0000

Data Index: 1226868 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 1.5652. Min Range: -1.5652

Max Act: 0.9257. Min Act: -0.0000

Data Index: 695358 (C4 (Web Text))

Max Activating Token Index: 796