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

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

Neuron 1872 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.3600. Min Act: -0.0000

Data Index: 130586 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1011465 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2964. Min Act: -0.0000

Data Index: 488751 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2952. Min Act: -0.0000

Data Index: 655118 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2951. Min Act: -0.0000

Data Index: 419561 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1216098 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1211356 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2901. Min Act: -0.0000

Data Index: 24404 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2797. Min Act: -0.0000

Data Index: 440241 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2656. Min Act: -0.0000

Data Index: 898669 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2753. Min Act: -0.0000

Data Index: 747894 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2636. Min Act: -0.0000

Data Index: 131154 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2729. Min Act: -0.0000

Data Index: 196424 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2641. Min Act: -0.0000

Data Index: 748911 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2717. Min Act: -0.0000

Data Index: 701343 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2621. Min Act: -0.0000

Data Index: 324906 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2614. Min Act: -0.0000

Data Index: 821961 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1012349 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2673. Min Act: -0.0000

Data Index: 903583 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.3600. Min Range: -0.3600

Max Act: 0.2638. Min Act: -0.0000

Data Index: 857474 (C4 (Web Text))

Max Activating Token Index: 329