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

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

Neuron 2910 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8618. Min Act: -0.0002

Data Index: 1517799 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8609. Min Act: -0.0002

Data Index: 1536816 (Python Code)

Max Activating Token Index: 44

Text #2

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8348. Min Act: -0.0002

Data Index: 1641404 (Python Code)

Max Activating Token Index: 910

Text #3

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7806. Min Act: -0.0002

Data Index: 1516093 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7930. Min Act: -0.0002

Data Index: 1590902 (Python Code)

Max Activating Token Index: 317

Text #5

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7873. Min Act: -0.0002

Data Index: 1635600 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7800. Min Act: -0.0002

Data Index: 1594136 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7715. Min Act: -0.0002

Data Index: 1533951 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7736. Min Act: -0.0002

Data Index: 1634771 (Python Code)

Max Activating Token Index: 105

Text #9

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7628. Min Act: -0.0002

Data Index: 1527564 (Python Code)

Max Activating Token Index: 795

Text #10

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7664. Min Act: -0.0002

Data Index: 1525062 (Python Code)

Max Activating Token Index: 121

Text #11

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7479. Min Act: -0.0002

Data Index: 1577776 (Python Code)

Max Activating Token Index: 729

Text #12

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7417. Min Act: -0.0002

Data Index: 1536417 (Python Code)

Max Activating Token Index: 769

Text #13

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7209. Min Act: -0.0002

Data Index: 1439985 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.6996. Min Act: -0.0002

Data Index: 1465850 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7144. Min Act: -0.0002

Data Index: 1491622 (Python Code)

Max Activating Token Index: 645

Text #16

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7109. Min Act: -0.0002

Data Index: 1440541 (Python Code)

Max Activating Token Index: 999

Text #17

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.6948. Min Act: -0.0002

Data Index: 1565504 (Python Code)

Max Activating Token Index: 207

Text #18

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7043. Min Act: -0.0002

Data Index: 1405836 (Python Code)

Max Activating Token Index: 789

Text #19

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.6715. Min Act: -0.0002

Data Index: 1599843 (Python Code)

Max Activating Token Index: 39