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

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

Neuron 4785 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.3698. Min Act: 0.0002

Data Index: 1403632 (Python Code)

Max Activating Token Index: 86

Text #1

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.2729. Min Act: -0.0000

Data Index: 1418079 (Python Code)

Max Activating Token Index: 647

Text #2

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.2761. Min Act: -0.0000

Data Index: 1618835 (Python Code)

Max Activating Token Index: 49

Text #3

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.1708. Min Act: -0.0000

Data Index: 1576919 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.2201. Min Act: -0.0000

Data Index: 1426199 (Python Code)

Max Activating Token Index: 278

Text #5

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.1317. Min Act: 0.0001

Data Index: 1601552 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.2307. Min Act: 0.0001

Data Index: 1494959 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.0676. Min Act: 0.0002

Data Index: 1623981 (Python Code)

Max Activating Token Index: 73

Text #8

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.1670. Min Act: -0.0000

Data Index: 1401779 (Python Code)

Max Activating Token Index: 840

Text #9

Max Range: 1.3698. Min Range: -1.3698

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1416642 (Python Code)

Max Activating Token Index: 700

Text #10

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1626881 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.0368. Min Act: 0.0001

Data Index: 1502066 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1580335 (Python Code)

Max Activating Token Index: 462

Text #13

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1450897 (Python Code)

Max Activating Token Index: 571

Text #14

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1404889 (Python Code)

Max Activating Token Index: 220

Text #15

Max Range: 1.3698. Min Range: -1.3698

Max Act: 0.9772. Min Act: 0.0002

Data Index: 1552063 (Python Code)

Max Activating Token Index: 90

Text #16

Max Range: 1.3698. Min Range: -1.3698

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1607887 (Python Code)

Max Activating Token Index: 500

Text #17

Max Range: 1.3698. Min Range: -1.3698

Max Act: 0.9584. Min Act: 0.0001

Data Index: 1524915 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 1.3698. Min Range: -1.3698

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1489363 (Python Code)

Max Activating Token Index: 106

Text #19

Max Range: 1.3698. Min Range: -1.3698

Max Act: 1.0172. Min Act: 0.0001

Data Index: 1570550 (Python Code)

Max Activating Token Index: 64