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

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

Neuron 3827 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1266845 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1307793 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1214589 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0832. Min Act: -0.0000

Data Index: 60508 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0825. Min Act: -0.0001

Data Index: 725420 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0846. Min Act: -0.0001

Data Index: 998257 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0815. Min Act: -0.0000

Data Index: 1507941 (Python Code)

Max Activating Token Index: 643

Text #7

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0670. Min Act: -0.0000

Data Index: 322926 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0771. Min Act: -0.0000

Data Index: 728453 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0816. Min Act: -0.0001

Data Index: 889187 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1321530 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0681. Min Act: -0.0000

Data Index: 312831 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0717. Min Act: -0.0000

Data Index: 424948 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1136364 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0633. Min Act: -0.0000

Data Index: 519470 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1153727 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1150435 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1599604 (Python Code)

Max Activating Token Index: 761

Text #18

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1350550 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1196219 (C4 (Web Text))

Max Activating Token Index: 67