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

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

Neuron 1515 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: 0.0747. Min Range: -0.0747

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1384204 (Python Code)

Max Activating Token Index: 72

Text #1

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1510152 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1482910 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1403450 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1645680 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1538901 (Python Code)

Max Activating Token Index: 61

Text #6

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0656. Min Act: -0.0001

Data Index: 898435 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1526235 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1557759 (Python Code)

Max Activating Token Index: 212

Text #9

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1624653 (Python Code)

Max Activating Token Index: 426

Text #10

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1525323 (Python Code)

Max Activating Token Index: 189

Text #11

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1371500 (Python Code)

Max Activating Token Index: 49

Text #12

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1597098 (Python Code)

Max Activating Token Index: 118

Text #13

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1599231 (Python Code)

Max Activating Token Index: 797

Text #14

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1399211 (Python Code)

Max Activating Token Index: 521

Text #15

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1654721 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1359810 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1402093 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1540806 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1393078 (Python Code)

Max Activating Token Index: 114