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

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

Neuron 1967 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.8392. Min Act: -0.0001

Data Index: 1433338 (Python Code)

Max Activating Token Index: 741

Text #1

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.1686. Min Act: -0.0001

Data Index: 1361904 (Python Code)

Max Activating Token Index: 217

Text #2

Max Range: 1.8392. Min Range: -1.8392

Max Act: 1.1418. Min Act: -0.0001

Data Index: 1365394 (Python Code)

Max Activating Token Index: 438

Text #3

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.8548. Min Act: -0.0001

Data Index: 1643786 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.9786. Min Act: -0.0001

Data Index: 1564023 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.8490. Min Act: -0.0001

Data Index: 1597848 (Python Code)

Max Activating Token Index: 428

Text #6

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.8616. Min Act: -0.0001

Data Index: 1529415 (Python Code)

Max Activating Token Index: 888

Text #7

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.8718. Min Act: -0.0001

Data Index: 1531878 (Python Code)

Max Activating Token Index: 351

Text #8

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.8209. Min Act: -0.0001

Data Index: 1372330 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.8409. Min Act: -0.0001

Data Index: 1463284 (Python Code)

Max Activating Token Index: 204

Text #10

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.8081. Min Act: -0.0001

Data Index: 1604575 (Python Code)

Max Activating Token Index: 121

Text #11

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.8465. Min Act: -0.0001

Data Index: 1478606 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.7653. Min Act: -0.0001

Data Index: 1530074 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.8099. Min Act: -0.0001

Data Index: 1636969 (Python Code)

Max Activating Token Index: 861

Text #14

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.7853. Min Act: -0.0001

Data Index: 1444517 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.7896. Min Act: -0.0001

Data Index: 1597584 (Python Code)

Max Activating Token Index: 67

Text #16

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.7521. Min Act: -0.0001

Data Index: 1548079 (Python Code)

Max Activating Token Index: 503

Text #17

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.7011. Min Act: -0.0001

Data Index: 1396535 (Python Code)

Max Activating Token Index: 681

Text #18

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.7836. Min Act: -0.0001

Data Index: 1559568 (Python Code)

Max Activating Token Index: 989

Text #19

Max Range: 1.8392. Min Range: -1.8392

Max Act: 0.7461. Min Act: -0.0001

Data Index: 1652828 (Python Code)

Max Activating Token Index: 86