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

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

Neuron 858 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.9269. Min Act: -0.0001

Data Index: 939038 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 1.0008. Min Range: -1.0008

Max Act: 1.0008. Min Act: -0.0001

Data Index: 639627 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.9832. Min Act: -0.0001

Data Index: 656295 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.7828. Min Act: -0.0001

Data Index: 1117135 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.8583. Min Act: -0.0001

Data Index: 580098 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.7873. Min Act: -0.0001

Data Index: 1232617 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.7942. Min Act: -0.0001

Data Index: 566055 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.8349. Min Act: -0.0001

Data Index: 667146 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.8192. Min Act: -0.0001

Data Index: 950319 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.7887. Min Act: -0.0001

Data Index: 218186 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.9055. Min Act: -0.0001

Data Index: 1088861 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.7639. Min Act: -0.0001

Data Index: 1261737 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.7298. Min Act: -0.0001

Data Index: 929525 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.7260. Min Act: -0.0001

Data Index: 8864 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.7642. Min Act: -0.0001

Data Index: 949526 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.6961. Min Act: -0.0001

Data Index: 247611 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.7590. Min Act: -0.0001

Data Index: 1190719 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.6192. Min Act: -0.0001

Data Index: 1156815 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.7250. Min Act: -0.0001

Data Index: 296135 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 1.0008. Min Range: -1.0008

Max Act: 0.7037. Min Act: -0.0001

Data Index: 70750 (C4 (Web Text))

Max Activating Token Index: 637