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

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

Neuron 5564 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.6694. Min Act: -0.0000

Data Index: 1281852 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.3843. Min Act: -0.0000

Data Index: 65841 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.2177. Min Act: -0.0000

Data Index: 741683 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.6195. Min Act: -0.0000

Data Index: 661481 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.2614. Min Act: -0.0000

Data Index: 1063569 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.3365. Min Act: -0.0000

Data Index: 468357 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.2385. Min Act: -0.0000

Data Index: 1087505 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.3075. Min Act: -0.0000

Data Index: 693516 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.1452. Min Act: -0.0000

Data Index: 267048 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.2403. Min Act: -0.0000

Data Index: 118147 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.0641. Min Act: -0.0000

Data Index: 730721 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.0245. Min Act: -0.0000

Data Index: 712359 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 2.6694. Min Range: -2.6694

Max Act: 1.8933. Min Act: -0.0000

Data Index: 42430 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.0421. Min Act: -0.0000

Data Index: 724727 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.2000. Min Act: -0.0000

Data Index: 326159 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.0865. Min Act: -0.0000

Data Index: 1028823 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 2.6694. Min Range: -2.6694

Max Act: 1.9961. Min Act: -0.0000

Data Index: 1234463 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.1957. Min Act: -0.0000

Data Index: 1016736 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 2.6694. Min Range: -2.6694

Max Act: 2.2199. Min Act: -0.0001

Data Index: 626199 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 2.6694. Min Range: -2.6694

Max Act: 1.9760. Min Act: -0.0000

Data Index: 881581 (C4 (Web Text))

Max Activating Token Index: 520