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

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

Neuron 1400 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: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1437713 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1579656 (Python Code)

Max Activating Token Index: 726

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1436737 (Python Code)

Max Activating Token Index: 664

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1377448 (Python Code)

Max Activating Token Index: 550

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1443982 (Python Code)

Max Activating Token Index: 241

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1512104 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1561221 (Python Code)

Max Activating Token Index: 522

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1436475 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1552766 (Python Code)

Max Activating Token Index: 967

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1466103 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1586732 (Python Code)

Max Activating Token Index: 137

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1511901 (Python Code)

Max Activating Token Index: 846

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1438592 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1568596 (Python Code)

Max Activating Token Index: 651

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0715. Min Act: -0.0001

Data Index: 1559057 (Python Code)

Max Activating Token Index: 580

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1641773 (Python Code)

Max Activating Token Index: 80

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1447753 (Python Code)

Max Activating Token Index: 660

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1511512 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1545613 (Python Code)

Max Activating Token Index: 64

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1462340 (Python Code)

Max Activating Token Index: 588