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

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

Neuron 194 in Layer 0

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: 0.6688. Min Range: -0.6688

Max Act: 0.6688. Min Act: -0.0001

Data Index: 1512674 (Python Code)

Max Activating Token Index: 170

Text #1

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.6586. Min Act: -0.0002

Data Index: 1568137 (Python Code)

Max Activating Token Index: 29

Text #2

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.6219. Min Act: -0.0001

Data Index: 1652242 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.6129. Min Act: -0.0001

Data Index: 1563015 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.6075. Min Act: -0.0001

Data Index: 1405101 (Python Code)

Max Activating Token Index: 591

Text #5

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5916. Min Act: -0.0002

Data Index: 1390776 (Python Code)

Max Activating Token Index: 586

Text #6

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5849. Min Act: -0.0001

Data Index: 1395741 (Python Code)

Max Activating Token Index: 465

Text #7

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5950. Min Act: -0.0001

Data Index: 1437373 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5840. Min Act: -0.0001

Data Index: 1513329 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5917. Min Act: -0.0002

Data Index: 1625620 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5852. Min Act: -0.0001

Data Index: 1529034 (Python Code)

Max Activating Token Index: 607

Text #11

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5703. Min Act: -0.0001

Data Index: 1522881 (Python Code)

Max Activating Token Index: 261

Text #12

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5704. Min Act: -0.0001

Data Index: 1642188 (Python Code)

Max Activating Token Index: 414

Text #13

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5682. Min Act: -0.0002

Data Index: 1399885 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5728. Min Act: -0.0001

Data Index: 1387966 (Python Code)

Max Activating Token Index: 647

Text #15

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5654. Min Act: -0.0001

Data Index: 1469825 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5708. Min Act: -0.0001

Data Index: 1405989 (Python Code)

Max Activating Token Index: 551

Text #17

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5657. Min Act: -0.0001

Data Index: 1369759 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5550. Min Act: -0.0002

Data Index: 1628722 (Python Code)

Max Activating Token Index: 192

Text #19

Max Range: 0.6688. Min Range: -0.6688

Max Act: 0.5616. Min Act: -0.0001

Data Index: 1639359 (Python Code)

Max Activating Token Index: 812