Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 674 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0696. Min Act: -0.0003

Data Index: 1472963 (Python Code)

Max Activating Token Index: 32

Text #1

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0658. Min Act: -0.0003

Data Index: 1404035 (Python Code)

Max Activating Token Index: 32

Text #2

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1394627 (Python Code)

Max Activating Token Index: 489

Text #3

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0624. Min Act: -0.0003

Data Index: 1647589 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1575671 (Python Code)

Max Activating Token Index: 697

Text #5

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1492805 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1459298 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1457002 (Python Code)

Max Activating Token Index: 152

Text #8

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1511946 (Python Code)

Max Activating Token Index: 130

Text #9

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1606165 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1599395 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0624. Min Act: -0.0003

Data Index: 1367450 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1446890 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1486961 (Python Code)

Max Activating Token Index: 724

Text #14

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1465755 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1426109 (Python Code)

Max Activating Token Index: 46

Text #16

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1411650 (Python Code)

Max Activating Token Index: 389

Text #17

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1488150 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1390031 (Python Code)

Max Activating Token Index: 951

Text #19

Max Range: 0.0696. Min Range: -0.0696

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1452671 (Python Code)

Max Activating Token Index: 15