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

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

Neuron 2272 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.3087. Min Act: -0.0001

Data Index: 943601 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.2803. Min Act: -0.0001

Data Index: 593144 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1663. Min Act: -0.0001

Data Index: 775069 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1999. Min Act: -0.0001

Data Index: 321374 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1915. Min Act: -0.0001

Data Index: 73294 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1028. Min Act: -0.0001

Data Index: 836144 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0665. Min Act: -0.0001

Data Index: 890531 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.0355. Min Act: -0.0001

Data Index: 834470 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1089. Min Act: -0.0001

Data Index: 1304116 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9832. Min Act: -0.0001

Data Index: 416149 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 1.3087. Min Range: -1.3087

Max Act: 1.1634. Min Act: -0.0001

Data Index: 333792 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9249. Min Act: -0.0001

Data Index: 653817 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8852. Min Act: -0.0001

Data Index: 441413 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9391. Min Act: -0.0001

Data Index: 137124 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9143. Min Act: -0.0001

Data Index: 403031 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9304. Min Act: -0.0001

Data Index: 68648 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9263. Min Act: -0.0001

Data Index: 375510 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.9173. Min Act: -0.0001

Data Index: 569770 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8020. Min Act: -0.0001

Data Index: 855590 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 1.3087. Min Range: -1.3087

Max Act: 0.8880. Min Act: -0.0001

Data Index: 752490 (C4 (Web Text))

Max Activating Token Index: 323