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

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

Neuron 4930 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.8928. Min Act: 0.0000

Data Index: 1560554 (Python Code)

Max Activating Token Index: 635

Text #1

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.7389. Min Act: -0.0000

Data Index: 1570993 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.7627. Min Act: -0.0000

Data Index: 1505005 (Python Code)

Max Activating Token Index: 404

Text #3

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.5870. Min Act: -0.0000

Data Index: 1652659 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.4096. Min Act: 0.0000

Data Index: 1492422 (Python Code)

Max Activating Token Index: 706

Text #5

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.4756. Min Act: 0.0001

Data Index: 1559420 (Python Code)

Max Activating Token Index: 359

Text #6

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.2774. Min Act: -0.0000

Data Index: 1614668 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.2614. Min Act: 0.0001

Data Index: 1494902 (Python Code)

Max Activating Token Index: 557

Text #8

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.2246. Min Act: 0.0001

Data Index: 1451523 (Python Code)

Max Activating Token Index: 653

Text #9

Max Range: 2.8928. Min Range: -2.8928

Max Act: 1.9715. Min Act: -0.0000

Data Index: 1546855 (Python Code)

Max Activating Token Index: 210

Text #10

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.1489. Min Act: 0.0000

Data Index: 1365635 (Python Code)

Max Activating Token Index: 189

Text #11

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.1378. Min Act: 0.0001

Data Index: 1596882 (Python Code)

Max Activating Token Index: 943

Text #12

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.1131. Min Act: -0.0000

Data Index: 1606531 (Python Code)

Max Activating Token Index: 882

Text #13

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.1614. Min Act: 0.0000

Data Index: 1653967 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.1566. Min Act: -0.0000

Data Index: 1426423 (Python Code)

Max Activating Token Index: 587

Text #15

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.1594. Min Act: -0.0000

Data Index: 1406078 (Python Code)

Max Activating Token Index: 676

Text #16

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.1717. Min Act: -0.0000

Data Index: 1394001 (Python Code)

Max Activating Token Index: 536

Text #17

Max Range: 2.8928. Min Range: -2.8928

Max Act: 2.0900. Min Act: -0.0000

Data Index: 1376181 (Python Code)

Max Activating Token Index: 222

Text #18

Max Range: 2.8928. Min Range: -2.8928

Max Act: 1.9765. Min Act: -0.0000

Data Index: 1419669 (Python Code)

Max Activating Token Index: 496

Text #19

Max Range: 2.8928. Min Range: -2.8928

Max Act: 1.9873. Min Act: -0.0000

Data Index: 1526879 (Python Code)

Max Activating Token Index: 346