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

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

Neuron 3931 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1585733 (Python Code)

Max Activating Token Index: 943

Text #1

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1413571 (Python Code)

Max Activating Token Index: 833

Text #2

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1613737 (Python Code)

Max Activating Token Index: 1017

Text #3

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1474080 (Python Code)

Max Activating Token Index: 422

Text #4

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1652177 (Python Code)

Max Activating Token Index: 350

Text #5

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1511118 (Python Code)

Max Activating Token Index: 273

Text #6

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1424955 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1408663 (Python Code)

Max Activating Token Index: 662

Text #8

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1372584 (Python Code)

Max Activating Token Index: 597

Text #9

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1655151 (Python Code)

Max Activating Token Index: 638

Text #10

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1528838 (Python Code)

Max Activating Token Index: 348

Text #11

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1567409 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1582802 (Python Code)

Max Activating Token Index: 752

Text #13

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1627667 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1483866 (Python Code)

Max Activating Token Index: 95

Text #15

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1785. Min Act: -0.0001

Data Index: 1630058 (Python Code)

Max Activating Token Index: 411

Text #16

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1437942 (Python Code)

Max Activating Token Index: 993

Text #17

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1572421 (Python Code)

Max Activating Token Index: 895

Text #18

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1535711 (Python Code)

Max Activating Token Index: 784

Text #19

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1416236 (Python Code)

Max Activating Token Index: 815