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

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

Neuron 4008 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.8667. Min Act: -0.0000

Data Index: 385748 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.8232. Min Act: 0.0001

Data Index: 794529 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.8005. Min Act: -0.0000

Data Index: 909701 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.8306. Min Act: 0.0004

Data Index: 143817 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.7761. Min Act: 0.0000

Data Index: 178070 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1268601 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.7361. Min Act: -0.0000

Data Index: 577722 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.7500. Min Act: 0.0004

Data Index: 1169806 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.7178. Min Act: 0.0001

Data Index: 331039 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.6996. Min Act: 0.0003

Data Index: 106139 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.7211. Min Act: -0.0000

Data Index: 656424 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.6993. Min Act: 0.0001

Data Index: 810610 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.7250. Min Act: 0.0002

Data Index: 577774 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.7011. Min Act: 0.0004

Data Index: 484806 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.6929. Min Act: 0.0001

Data Index: 1346598 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1057534 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.6800. Min Act: -0.0000

Data Index: 454082 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.6594. Min Act: -0.0000

Data Index: 96746 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.6721. Min Act: 0.0000

Data Index: 809014 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.8667. Min Range: -0.8667

Max Act: 0.6618. Min Act: -0.0000

Data Index: 459888 (C4 (Web Text))

Max Activating Token Index: 297