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

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

Neuron 925 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.3112. Min Act: -0.0000

Data Index: 1524120 (Python Code)

Max Activating Token Index: 420

Text #1

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.2894. Min Act: -0.0000

Data Index: 1419452 (Python Code)

Max Activating Token Index: 558

Text #2

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1404938 (Python Code)

Max Activating Token Index: 507

Text #3

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.2332. Min Act: -0.0000

Data Index: 1452878 (Python Code)

Max Activating Token Index: 630

Text #4

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1418616 (Python Code)

Max Activating Token Index: 865

Text #5

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1386280 (Python Code)

Max Activating Token Index: 740

Text #6

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1903. Min Act: -0.0000

Data Index: 1450331 (Python Code)

Max Activating Token Index: 414

Text #7

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1136. Min Act: -0.0000

Data Index: 1430142 (Python Code)

Max Activating Token Index: 714

Text #8

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1080. Min Act: -0.0000

Data Index: 1482597 (Python Code)

Max Activating Token Index: 779

Text #9

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1457. Min Act: -0.0000

Data Index: 1364596 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1533657 (Python Code)

Max Activating Token Index: 1018

Text #11

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1522969 (Python Code)

Max Activating Token Index: 816

Text #12

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1513573 (Python Code)

Max Activating Token Index: 461

Text #13

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1793. Min Act: -0.0000

Data Index: 1369502 (Python Code)

Max Activating Token Index: 420

Text #14

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1512666 (Python Code)

Max Activating Token Index: 563

Text #15

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.0081. Min Act: -0.0000

Data Index: 1612242 (Python Code)

Max Activating Token Index: 331

Text #16

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1587980 (Python Code)

Max Activating Token Index: 507

Text #17

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1518922 (Python Code)

Max Activating Token Index: 474

Text #18

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.2652. Min Act: -0.0000

Data Index: 1477413 (Python Code)

Max Activating Token Index: 368

Text #19

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.0833. Min Act: -0.0000

Data Index: 1469262 (Python Code)

Max Activating Token Index: 916