Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 487 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.8502. Min Act: -0.0001

Data Index: 1466743 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.8007. Min Act: -0.0001

Data Index: 1557221 (Python Code)

Max Activating Token Index: 377

Text #2

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7607. Min Act: -0.0002

Data Index: 685429 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7659. Min Act: -0.0001

Data Index: 1612736 (Python Code)

Max Activating Token Index: 95

Text #4

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7502. Min Act: -0.0001

Data Index: 1467284 (Python Code)

Max Activating Token Index: 907

Text #5

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7185. Min Act: -0.0001

Data Index: 1520793 (Python Code)

Max Activating Token Index: 993

Text #6

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7291. Min Act: -0.0001

Data Index: 1366213 (Python Code)

Max Activating Token Index: 752

Text #7

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6923. Min Act: -0.0002

Data Index: 1062168 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6828. Min Act: -0.0002

Data Index: 54793 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7496. Min Act: -0.0001

Data Index: 1511125 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7123. Min Act: -0.0001

Data Index: 1530387 (Python Code)

Max Activating Token Index: 737

Text #11

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7128. Min Act: -0.0001

Data Index: 1438296 (Python Code)

Max Activating Token Index: 434

Text #12

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.7164. Min Act: -0.0001

Data Index: 1518424 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6788. Min Act: -0.0002

Data Index: 742681 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6924. Min Act: -0.0002

Data Index: 988257 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6897. Min Act: -0.0001

Data Index: 1389816 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6651. Min Act: -0.0002

Data Index: 702308 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6618. Min Act: -0.0002

Data Index: 814042 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6609. Min Act: -0.0002

Data Index: 1224225 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.8502. Min Range: -0.8502

Max Act: 0.6984. Min Act: -0.0002

Data Index: 1155257 (C4 (Web Text))

Max Activating Token Index: 848