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

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

Neuron 5000 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: 0.9149. Min Range: -0.9149

Max Act: 0.8714. Min Act: -0.0000

Data Index: 742535 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.9149. Min Act: -0.0000

Data Index: 604085 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7608. Min Act: -0.0000

Data Index: 897150 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7626. Min Act: -0.0000

Data Index: 463313 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.7021. Min Act: -0.0000

Data Index: 833165 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1156690 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6345. Min Act: -0.0000

Data Index: 512077 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6001. Min Act: -0.0000

Data Index: 891846 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6284. Min Act: -0.0000

Data Index: 721059 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.5640. Min Act: -0.0000

Data Index: 13953 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6303. Min Act: -0.0000

Data Index: 525154 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.6222. Min Act: -0.0000

Data Index: 403619 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1201932 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.5579. Min Act: -0.0000

Data Index: 950977 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.5619. Min Act: -0.0000

Data Index: 341837 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.5039. Min Act: -0.0000

Data Index: 379565 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.5644. Min Act: -0.0000

Data Index: 880842 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1147974 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.5091. Min Act: -0.0000

Data Index: 836899 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.9149. Min Range: -0.9149

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1109200 (C4 (Web Text))

Max Activating Token Index: 392