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

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

Neuron 561 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: 0.0800. Min Range: -0.0800

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1579621 (Python Code)

Max Activating Token Index: 678

Text #1

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1489944 (Python Code)

Max Activating Token Index: 955

Text #2

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1561435 (Python Code)

Max Activating Token Index: 768

Text #3

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1390216 (Python Code)

Max Activating Token Index: 921

Text #4

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1380907 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1556169 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1650388 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1509647 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1394486 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1623210 (Python Code)

Max Activating Token Index: 330

Text #10

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1419014 (Python Code)

Max Activating Token Index: 761

Text #11

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1375597 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1384362 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1412567 (Python Code)

Max Activating Token Index: 35

Text #14

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1433904 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1523079 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1380161 (Python Code)

Max Activating Token Index: 186

Text #17

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1540605 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1574775 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1414723 (Python Code)

Max Activating Token Index: 475