Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2902 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7612. Min Range: -2.7612

Max Act: 2.7612. Min Act: -0.0000

Data Index: 1421863 (Python Code)

Max Activating Token Index: 617

Text #1

Max Range: 2.7612. Min Range: -2.7612

Max Act: 2.2098. Min Act: -0.0000

Data Index: 1636079 (Python Code)

Max Activating Token Index: 926

Text #2

Max Range: 2.7612. Min Range: -2.7612

Max Act: 2.3291. Min Act: -0.0000

Data Index: 1418525 (Python Code)

Max Activating Token Index: 882

Text #3

Max Range: 2.7612. Min Range: -2.7612

Max Act: 2.1894. Min Act: -0.0000

Data Index: 1554557 (Python Code)

Max Activating Token Index: 240

Text #4

Max Range: 2.7612. Min Range: -2.7612

Max Act: 2.1621. Min Act: -0.0000

Data Index: 1392430 (Python Code)

Max Activating Token Index: 643

Text #5

Max Range: 2.7612. Min Range: -2.7612

Max Act: 2.2616. Min Act: -0.0000

Data Index: 1490619 (Python Code)

Max Activating Token Index: 119

Text #6

Max Range: 2.7612. Min Range: -2.7612

Max Act: 2.1585. Min Act: 0.0001

Data Index: 1376188 (Python Code)

Max Activating Token Index: 418

Text #7

Max Range: 2.7612. Min Range: -2.7612

Max Act: 2.0870. Min Act: -0.0000

Data Index: 1562148 (Python Code)

Max Activating Token Index: 710

Text #8

Max Range: 2.7612. Min Range: -2.7612

Max Act: 1.8940. Min Act: -0.0000

Data Index: 1581710 (Python Code)

Max Activating Token Index: 704

Text #9

Max Range: 2.7612. Min Range: -2.7612

Max Act: 1.9977. Min Act: 0.0001

Data Index: 1605203 (Python Code)

Max Activating Token Index: 152

Text #10

Max Range: 2.7612. Min Range: -2.7612

Max Act: 2.0881. Min Act: -0.0000

Data Index: 1645710 (Python Code)

Max Activating Token Index: 188

Text #11

Max Range: 2.7612. Min Range: -2.7612

Max Act: 2.0989. Min Act: -0.0000

Data Index: 1424563 (Python Code)

Max Activating Token Index: 673

Text #12

Max Range: 2.7612. Min Range: -2.7612

Max Act: 1.9788. Min Act: -0.0000

Data Index: 1496946 (Python Code)

Max Activating Token Index: 705

Text #13

Max Range: 2.7612. Min Range: -2.7612

Max Act: 1.8469. Min Act: -0.0000

Data Index: 1405842 (Python Code)

Max Activating Token Index: 258

Text #14

Max Range: 2.7612. Min Range: -2.7612

Max Act: 1.8656. Min Act: 0.0000

Data Index: 1412193 (Python Code)

Max Activating Token Index: 170

Text #15

Max Range: 2.7612. Min Range: -2.7612

Max Act: 1.9317. Min Act: -0.0000

Data Index: 1492296 (Python Code)

Max Activating Token Index: 420

Text #16

Max Range: 2.7612. Min Range: -2.7612

Max Act: 1.9166. Min Act: -0.0000

Data Index: 1436081 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 2.7612. Min Range: -2.7612

Max Act: 1.9262. Min Act: 0.0000

Data Index: 1574821 (Python Code)

Max Activating Token Index: 402

Text #18

Max Range: 2.7612. Min Range: -2.7612

Max Act: 1.9170. Min Act: 0.0000

Data Index: 1404924 (Python Code)

Max Activating Token Index: 693

Text #19

Max Range: 2.7612. Min Range: -2.7612

Max Act: 1.8734. Min Act: -0.0000

Data Index: 1397674 (Python Code)

Max Activating Token Index: 42