Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2747 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.1287. Min Act: -0.0001

Data Index: 910114 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.0945. Min Act: -0.0001

Data Index: 1103308 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.1717. Min Act: -0.0001

Data Index: 260793 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.1110. Min Act: -0.0001

Data Index: 553682 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.0406. Min Act: -0.0001

Data Index: 1304767 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.1339. Min Act: -0.0001

Data Index: 1057326 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.1885. Min Act: -0.0001

Data Index: 118886 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.0075. Min Act: -0.0001

Data Index: 196548 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 3.2976. Min Range: -3.2976

Max Act: 2.9821. Min Act: -0.0001

Data Index: 897913 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 3.2976. Min Range: -3.2976

Max Act: 2.6918. Min Act: -0.0001

Data Index: 305570 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 3.2976. Min Range: -3.2976

Max Act: 2.9770. Min Act: -0.0001

Data Index: 661579 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 3.2976. Min Range: -3.2976

Max Act: 2.6173. Min Act: -0.0001

Data Index: 413724 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 3.2976. Min Range: -3.2976

Max Act: 2.5535. Min Act: -0.0001

Data Index: 1193519 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.2976. Min Act: -0.0001

Data Index: 270835 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.1825. Min Act: -0.0001

Data Index: 1311605 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 3.2976. Min Range: -3.2976

Max Act: 2.8119. Min Act: -0.0001

Data Index: 588325 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.0132. Min Act: -0.0001

Data Index: 466343 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 3.2976. Min Range: -3.2976

Max Act: 2.6842. Min Act: -0.0001

Data Index: 613019 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 3.2976. Min Range: -3.2976

Max Act: 3.1176. Min Act: -0.0001

Data Index: 65913 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 3.2976. Min Range: -3.2976

Max Act: 2.4700. Min Act: -0.0001

Data Index: 726890 (C4 (Web Text))

Max Activating Token Index: 218