Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 64 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1905. Min Act: -0.0002

Data Index: 1406721 (Python Code)

Max Activating Token Index: 655

Text #1

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1491587 (Python Code)

Max Activating Token Index: 676

Text #2

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1730. Min Act: -0.0002

Data Index: 1431442 (Python Code)

Max Activating Token Index: 624

Text #3

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1757. Min Act: -0.0002

Data Index: 1374573 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1558. Min Act: -0.0002

Data Index: 1512676 (Python Code)

Max Activating Token Index: 967

Text #5

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1609. Min Act: -0.0002

Data Index: 1619773 (Python Code)

Max Activating Token Index: 678

Text #6

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1633. Min Act: -0.0002

Data Index: 1555548 (Python Code)

Max Activating Token Index: 394

Text #7

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1596. Min Act: -0.0002

Data Index: 1395096 (Python Code)

Max Activating Token Index: 724

Text #8

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1601. Min Act: -0.0002

Data Index: 1648909 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1611. Min Act: -0.0002

Data Index: 1576347 (Python Code)

Max Activating Token Index: 768

Text #10

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1556. Min Act: -0.0002

Data Index: 1567823 (Python Code)

Max Activating Token Index: 143

Text #11

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1503. Min Act: -0.0002

Data Index: 1611634 (Python Code)

Max Activating Token Index: 1020

Text #12

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1535. Min Act: -0.0002

Data Index: 1409572 (Python Code)

Max Activating Token Index: 173

Text #13

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1558. Min Act: -0.0002

Data Index: 1594871 (Python Code)

Max Activating Token Index: 460

Text #14

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1519. Min Act: -0.0002

Data Index: 1640240 (Python Code)

Max Activating Token Index: 446

Text #15

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1483. Min Act: -0.0002

Data Index: 1375261 (Python Code)

Max Activating Token Index: 668

Text #16

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1473. Min Act: -0.0002

Data Index: 1628181 (Python Code)

Max Activating Token Index: 888

Text #17

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1506. Min Act: -0.0002

Data Index: 1548909 (Python Code)

Max Activating Token Index: 395

Text #18

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1414. Min Act: -0.0002

Data Index: 1543818 (Python Code)

Max Activating Token Index: 924

Text #19

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1454. Min Act: -0.0002

Data Index: 1466456 (Python Code)

Max Activating Token Index: 504