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

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

Neuron 461 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2606. Min Range: -1.2606

Max Act: 1.2162. Min Act: -0.0000

Data Index: 847964 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 1.2606. Min Range: -1.2606

Max Act: 1.1340. Min Act: -0.0000

Data Index: 755270 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 1.2606. Min Range: -1.2606

Max Act: 1.2606. Min Act: -0.0000

Data Index: 1190433 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.9851. Min Act: -0.0000

Data Index: 445744 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1048430 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.9765. Min Act: -0.0000

Data Index: 520768 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.9035. Min Act: -0.0000

Data Index: 889717 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.9578. Min Act: -0.0000

Data Index: 838356 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.9068. Min Act: -0.0000

Data Index: 3329 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.9981. Min Act: -0.0000

Data Index: 102151 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.9236. Min Act: -0.0000

Data Index: 842229 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1119319 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.8126. Min Act: -0.0000

Data Index: 331613 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.8555. Min Act: -0.0000

Data Index: 56184 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.8441. Min Act: -0.0000

Data Index: 43792 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1198905 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1196690 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.8126. Min Act: -0.0000

Data Index: 72085 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1212828 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.2606. Min Range: -1.2606

Max Act: 0.7500. Min Act: -0.0000

Data Index: 912175 (C4 (Web Text))

Max Activating Token Index: 883