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

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

Neuron 1050 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1564. Min Range: -1.1564

Max Act: 1.1564. Min Act: -0.0001

Data Index: 736546 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 1.1564. Min Range: -1.1564

Max Act: 1.0458. Min Act: -0.0001

Data Index: 476437 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.8991. Min Act: -0.0001

Data Index: 145630 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.8714. Min Act: -0.0001

Data Index: 215409 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.8042. Min Act: -0.0001

Data Index: 120981 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.8397. Min Act: -0.0001

Data Index: 1147528 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.7416. Min Act: -0.0001

Data Index: 13801 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.7225. Min Act: -0.0001

Data Index: 17538 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.7293. Min Act: -0.0001

Data Index: 737278 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.6800. Min Act: -0.0001

Data Index: 235874 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.7185. Min Act: -0.0001

Data Index: 559905 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1162712 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.6892. Min Act: -0.0001

Data Index: 878104 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.6790. Min Act: -0.0001

Data Index: 422729 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.6511. Min Act: -0.0001

Data Index: 491312 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.6825. Min Act: -0.0001

Data Index: 804229 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.6788. Min Act: -0.0001

Data Index: 33100 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.6178. Min Act: -0.0001

Data Index: 677337 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.6294. Min Act: -0.0001

Data Index: 916194 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 1.1564. Min Range: -1.1564

Max Act: 0.6889. Min Act: -0.0001

Data Index: 1215790 (C4 (Web Text))

Max Activating Token Index: 821