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

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

Neuron 3671 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: 0.9731. Min Range: -0.9731

Max Act: 0.9731. Min Act: -0.0002

Data Index: 1573725 (Python Code)

Max Activating Token Index: 782

Text #1

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9442. Min Act: -0.0002

Data Index: 1449418 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9013. Min Act: -0.0002

Data Index: 1404208 (Python Code)

Max Activating Token Index: 877

Text #3

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9028. Min Act: -0.0002

Data Index: 1516184 (Python Code)

Max Activating Token Index: 765

Text #4

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8982. Min Act: -0.0002

Data Index: 1494806 (Python Code)

Max Activating Token Index: 336

Text #5

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8901. Min Act: -0.0002

Data Index: 1598771 (Python Code)

Max Activating Token Index: 730

Text #6

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8881. Min Act: -0.0002

Data Index: 1374813 (Python Code)

Max Activating Token Index: 101

Text #7

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8838. Min Act: -0.0002

Data Index: 1539569 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8922. Min Act: -0.0002

Data Index: 1555387 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8824. Min Act: -0.0002

Data Index: 1653975 (Python Code)

Max Activating Token Index: 76

Text #10

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8864. Min Act: -0.0002

Data Index: 1387958 (Python Code)

Max Activating Token Index: 77

Text #11

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8661. Min Act: -0.0002

Data Index: 1529455 (Python Code)

Max Activating Token Index: 93

Text #12

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8798. Min Act: -0.0002

Data Index: 1543069 (Python Code)

Max Activating Token Index: 341

Text #13

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8583. Min Act: -0.0002

Data Index: 1367695 (Python Code)

Max Activating Token Index: 808

Text #14

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8427. Min Act: -0.0002

Data Index: 1521029 (Python Code)

Max Activating Token Index: 752

Text #15

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8388. Min Act: -0.0002

Data Index: 1376739 (Python Code)

Max Activating Token Index: 200

Text #16

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8387. Min Act: -0.0002

Data Index: 1442086 (Python Code)

Max Activating Token Index: 1015

Text #17

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8456. Min Act: -0.0002

Data Index: 1521449 (Python Code)

Max Activating Token Index: 714

Text #18

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8258. Min Act: -0.0002

Data Index: 1609305 (Python Code)

Max Activating Token Index: 560

Text #19

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8341. Min Act: -0.0002

Data Index: 1554402 (Python Code)

Max Activating Token Index: 87