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

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

Neuron 3066 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.8803. Min Act: -0.0001

Data Index: 788165 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.8351. Min Act: -0.0001

Data Index: 1270310 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.8420. Min Act: -0.0001

Data Index: 680618 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.8252. Min Act: -0.0001

Data Index: 787983 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7811. Min Act: -0.0001

Data Index: 1055281 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7985. Min Act: -0.0001

Data Index: 443213 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.8197. Min Act: -0.0001

Data Index: 568273 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7245. Min Act: -0.0001

Data Index: 467603 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.6686. Min Act: -0.0001

Data Index: 342561 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7210. Min Act: -0.0001

Data Index: 165572 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.6252. Min Act: -0.0001

Data Index: 1043662 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7425. Min Act: -0.0001

Data Index: 846596 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7226. Min Act: -0.0001

Data Index: 677981 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7061. Min Act: -0.0001

Data Index: 665242 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7105. Min Act: -0.0001

Data Index: 426686 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7078. Min Act: -0.0001

Data Index: 365807 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7058. Min Act: -0.0001

Data Index: 1099475 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7233. Min Act: -0.0001

Data Index: 310873 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7000. Min Act: -0.0001

Data Index: 750408 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.6828. Min Act: -0.0001

Data Index: 529647 (C4 (Web Text))

Max Activating Token Index: 212