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

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

Neuron 560 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: 1.3719. Min Range: -1.3719

Max Act: 1.3719. Min Act: -0.0000

Data Index: 681409 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.3719. Min Range: -1.3719

Max Act: 1.1338. Min Act: -0.0000

Data Index: 1647298 (Python Code)

Max Activating Token Index: 262

Text #2

Max Range: 1.3719. Min Range: -1.3719

Max Act: 1.0919. Min Act: -0.0000

Data Index: 683748 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 1.3719. Min Range: -1.3719

Max Act: 1.0385. Min Act: -0.0000

Data Index: 731872 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 1.3719. Min Range: -1.3719

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1239358 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 1.3719. Min Range: -1.3719

Max Act: 1.0891. Min Act: -0.0000

Data Index: 537262 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.3719. Min Range: -1.3719

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1514203 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 1.3719. Min Range: -1.3719

Max Act: 1.0416. Min Act: -0.0000

Data Index: 404321 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1522706 (Python Code)

Max Activating Token Index: 255

Text #9

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.9881. Min Act: -0.0000

Data Index: 18251 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.9943. Min Act: -0.0000

Data Index: 930954 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.9040. Min Act: -0.0000

Data Index: 189147 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1039123 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1075445 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.8908. Min Act: -0.0000

Data Index: 549393 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1133636 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.7870. Min Act: -0.0000

Data Index: 560012 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1403267 (Python Code)

Max Activating Token Index: 68

Text #18

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.8359. Min Act: -0.0000

Data Index: 401895 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 1.3719. Min Range: -1.3719

Max Act: 0.8346. Min Act: -0.0000

Data Index: 1593586 (Python Code)

Max Activating Token Index: 83