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

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

Neuron 2012 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: 0.0904. Min Range: -0.0904

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1366717 (Python Code)

Max Activating Token Index: 600

Text #1

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1067608 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1435718 (Python Code)

Max Activating Token Index: 372

Text #3

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1438096 (Python Code)

Max Activating Token Index: 769

Text #4

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1587695 (Python Code)

Max Activating Token Index: 106

Text #5

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1412344 (Python Code)

Max Activating Token Index: 163

Text #6

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1585864 (Python Code)

Max Activating Token Index: 730

Text #7

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1444036 (Python Code)

Max Activating Token Index: 574

Text #8

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1394873 (Python Code)

Max Activating Token Index: 180

Text #9

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1505227 (Python Code)

Max Activating Token Index: 349

Text #10

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1376144 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1622256 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0807. Min Act: -0.0002

Data Index: 807383 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1424262 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1582455 (Python Code)

Max Activating Token Index: 589

Text #15

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1570856 (Python Code)

Max Activating Token Index: 946

Text #16

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1531673 (Python Code)

Max Activating Token Index: 201

Text #17

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1377292 (Python Code)

Max Activating Token Index: 578

Text #18

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1453542 (Python Code)

Max Activating Token Index: 967

Text #19

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1486689 (Python Code)

Max Activating Token Index: 774