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

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

Neuron 3710 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.7887. Min Act: -0.0000

Data Index: 185159 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.6120. Min Act: -0.0000

Data Index: 902716 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.5857. Min Act: -0.0000

Data Index: 650414 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.6374. Min Act: -0.0000

Data Index: 665877 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1252928 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.6082. Min Act: -0.0000

Data Index: 345616 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1165455 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1137479 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.5311. Min Act: -0.0000

Data Index: 943865 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.5217. Min Act: -0.0000

Data Index: 15090 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.5500. Min Act: -0.0000

Data Index: 994711 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.5173. Min Act: -0.0000

Data Index: 633883 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1001138 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.4847. Min Act: -0.0000

Data Index: 295265 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.4679. Min Act: 0.0000

Data Index: 1340659 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.5135. Min Act: -0.0000

Data Index: 822336 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.4850. Min Act: -0.0000

Data Index: 735247 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.4488. Min Act: -0.0000

Data Index: 624844 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1172966 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.7887. Min Range: -0.7887

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1091519 (C4 (Web Text))

Max Activating Token Index: 91