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

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

Neuron 6022 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: 0.9439. Min Range: -0.9439

Max Act: 0.9439. Min Act: -0.0002

Data Index: 1598733 (Python Code)

Max Activating Token Index: 916

Text #1

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.9333. Min Act: -0.0002

Data Index: 1387545 (Python Code)

Max Activating Token Index: 42

Text #2

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.9367. Min Act: -0.0002

Data Index: 1382443 (Python Code)

Max Activating Token Index: 1004

Text #3

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8981. Min Act: -0.0002

Data Index: 1496532 (Python Code)

Max Activating Token Index: 426

Text #4

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8978. Min Act: -0.0002

Data Index: 1426080 (Python Code)

Max Activating Token Index: 929

Text #5

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.9020. Min Act: -0.0002

Data Index: 1594950 (Python Code)

Max Activating Token Index: 927

Text #6

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.9012. Min Act: -0.0002

Data Index: 1399976 (Python Code)

Max Activating Token Index: 952

Text #7

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8927. Min Act: -0.0002

Data Index: 1617356 (Python Code)

Max Activating Token Index: 164

Text #8

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8846. Min Act: -0.0002

Data Index: 1490842 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8899. Min Act: -0.0002

Data Index: 1447905 (Python Code)

Max Activating Token Index: 193

Text #10

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8752. Min Act: -0.0002

Data Index: 1373545 (Python Code)

Max Activating Token Index: 657

Text #11

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8808. Min Act: -0.0002

Data Index: 1468669 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8560. Min Act: -0.0002

Data Index: 1560099 (Python Code)

Max Activating Token Index: 993

Text #13

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8658. Min Act: -0.0002

Data Index: 1406320 (Python Code)

Max Activating Token Index: 239

Text #14

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8609. Min Act: -0.0002

Data Index: 1442172 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8570. Min Act: -0.0002

Data Index: 1491718 (Python Code)

Max Activating Token Index: 1013

Text #16

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8507. Min Act: -0.0002

Data Index: 1526735 (Python Code)

Max Activating Token Index: 268

Text #17

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8518. Min Act: -0.0002

Data Index: 1642964 (Python Code)

Max Activating Token Index: 1000

Text #18

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8638. Min Act: -0.0002

Data Index: 1373349 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 0.9439. Min Range: -0.9439

Max Act: 0.8644. Min Act: -0.0002

Data Index: 1562696 (Python Code)

Max Activating Token Index: 134