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

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

Neuron 2500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.9867. Min Act: -0.0001

Data Index: 55786 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8715. Min Act: -0.0001

Data Index: 1097497 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8897. Min Act: -0.0001

Data Index: 1094204 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.8332. Min Act: -0.0001

Data Index: 461196 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7929. Min Act: -0.0001

Data Index: 1295932 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7783. Min Act: -0.0001

Data Index: 147521 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7642. Min Act: -0.0001

Data Index: 264764 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7917. Min Act: -0.0001

Data Index: 514414 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7484. Min Act: -0.0001

Data Index: 590988 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7169. Min Act: -0.0001

Data Index: 1282683 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7326. Min Act: -0.0001

Data Index: 303625 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7342. Min Act: -0.0001

Data Index: 438882 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7337. Min Act: -0.0001

Data Index: 304244 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7516. Min Act: -0.0000

Data Index: 85496 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7518. Min Act: -0.0001

Data Index: 1008176 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7216. Min Act: -0.0000

Data Index: 129875 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.6832. Min Act: -0.0001

Data Index: 142080 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7578. Min Act: -0.0001

Data Index: 316874 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7088. Min Act: -0.0001

Data Index: 937972 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.9867. Min Range: -0.9867

Max Act: 0.7250. Min Act: -0.0001

Data Index: 227953 (C4 (Web Text))

Max Activating Token Index: 460