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

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

Neuron 3087 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: 2.8467. Min Range: -2.8467

Max Act: 2.8467. Min Act: -0.0000

Data Index: 122549 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.6359. Min Act: -0.0000

Data Index: 719323 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.5952. Min Act: -0.0000

Data Index: 435336 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.4287. Min Act: -0.0000

Data Index: 218832 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.3752. Min Act: -0.0000

Data Index: 1315979 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.2277. Min Act: -0.0000

Data Index: 1217038 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.9890. Min Act: -0.0000

Data Index: 1292246 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.2068. Min Act: -0.0000

Data Index: 321717 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.9985. Min Act: -0.0000

Data Index: 1035692 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 2.8467. Min Range: -2.8467

Max Act: 2.1167. Min Act: -0.0000

Data Index: 157621 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.9519. Min Act: -0.0000

Data Index: 513005 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.9141. Min Act: -0.0000

Data Index: 291518 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.9020. Min Act: -0.0000

Data Index: 1050248 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.7872. Min Act: -0.0000

Data Index: 1217153 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.7449. Min Act: -0.0000

Data Index: 551489 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.9173. Min Act: -0.0000

Data Index: 259636 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.7988. Min Act: -0.0000

Data Index: 972908 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.7594. Min Act: -0.0000

Data Index: 666629 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.7871. Min Act: -0.0000

Data Index: 684241 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 2.8467. Min Range: -2.8467

Max Act: 1.7248. Min Act: -0.0000

Data Index: 973255 (C4 (Web Text))

Max Activating Token Index: 504