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

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

Neuron 1895 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1387798 (Python Code)

Max Activating Token Index: 110

Text #1

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1563592 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1406669 (Python Code)

Max Activating Token Index: 164

Text #3

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1390407 (Python Code)

Max Activating Token Index: 167

Text #4

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1615065 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1469208 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1489430 (Python Code)

Max Activating Token Index: 404

Text #7

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1368141 (Python Code)

Max Activating Token Index: 402

Text #8

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1388720 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1635532 (Python Code)

Max Activating Token Index: 137

Text #10

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1523761 (Python Code)

Max Activating Token Index: 102

Text #11

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1493220 (Python Code)

Max Activating Token Index: 71

Text #12

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1525777 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1366524 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1515358 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1453018 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1612946 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1551176 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1536735 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1586758 (Python Code)

Max Activating Token Index: 46