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

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

Neuron 3673 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1496790 (Python Code)

Max Activating Token Index: 996

Text #1

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1421312 (Python Code)

Max Activating Token Index: 849

Text #2

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1606209 (Python Code)

Max Activating Token Index: 990

Text #3

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7751. Min Act: -0.0000

Data Index: 1500375 (Python Code)

Max Activating Token Index: 751

Text #4

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1387081 (Python Code)

Max Activating Token Index: 318

Text #5

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1468617 (Python Code)

Max Activating Token Index: 641

Text #6

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.7421. Min Act: -0.0000

Data Index: 1415860 (Python Code)

Max Activating Token Index: 208

Text #7

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1648743 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1571936 (Python Code)

Max Activating Token Index: 435

Text #9

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1566418 (Python Code)

Max Activating Token Index: 420

Text #10

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1409595 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1491527 (Python Code)

Max Activating Token Index: 794

Text #12

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1395672 (Python Code)

Max Activating Token Index: 806

Text #13

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1598896 (Python Code)

Max Activating Token Index: 849

Text #14

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1475733 (Python Code)

Max Activating Token Index: 400

Text #15

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1373491 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1368743 (Python Code)

Max Activating Token Index: 916

Text #17

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1578381 (Python Code)

Max Activating Token Index: 1003

Text #18

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1557573 (Python Code)

Max Activating Token Index: 709

Text #19

Max Range: 0.8963. Min Range: -0.8963

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1415214 (Python Code)

Max Activating Token Index: 923