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

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

Neuron 4100 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: 0.2056. Min Range: -0.2056

Max Act: 0.2056. Min Act: -0.0002

Data Index: 1555235 (Python Code)

Max Activating Token Index: 192

Text #1

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1939. Min Act: -0.0002

Data Index: 1449938 (Python Code)

Max Activating Token Index: 721

Text #2

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1790. Min Act: -0.0002

Data Index: 1446395 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1724. Min Act: -0.0002

Data Index: 1460840 (Python Code)

Max Activating Token Index: 148

Text #4

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1905. Min Act: -0.0002

Data Index: 1365713 (Python Code)

Max Activating Token Index: 900

Text #5

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1858. Min Act: -0.0002

Data Index: 1367778 (Python Code)

Max Activating Token Index: 232

Text #6

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1834. Min Act: -0.0002

Data Index: 1554405 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1799. Min Act: -0.0002

Data Index: 1373588 (Python Code)

Max Activating Token Index: 502

Text #8

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1858. Min Act: -0.0002

Data Index: 1560908 (Python Code)

Max Activating Token Index: 832

Text #9

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1735. Min Act: -0.0002

Data Index: 1640882 (Python Code)

Max Activating Token Index: 516

Text #10

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1921. Min Act: -0.0002

Data Index: 1590324 (Python Code)

Max Activating Token Index: 476

Text #11

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1841. Min Act: -0.0002

Data Index: 1460168 (Python Code)

Max Activating Token Index: 710

Text #12

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1768. Min Act: -0.0002

Data Index: 1500528 (Python Code)

Max Activating Token Index: 805

Text #13

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1845. Min Act: -0.0002

Data Index: 1504344 (Python Code)

Max Activating Token Index: 323

Text #14

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1771. Min Act: -0.0002

Data Index: 1617034 (Python Code)

Max Activating Token Index: 401

Text #15

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1798. Min Act: -0.0002

Data Index: 1337457 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1731. Min Act: -0.0002

Data Index: 1554288 (Python Code)

Max Activating Token Index: 547

Text #17

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1691. Min Act: -0.0002

Data Index: 1613133 (Python Code)

Max Activating Token Index: 852

Text #18

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1704. Min Act: -0.0002

Data Index: 1420348 (Python Code)

Max Activating Token Index: 808

Text #19

Max Range: 0.2056. Min Range: -0.2056

Max Act: 0.1643. Min Act: -0.0002

Data Index: 1561065 (Python Code)

Max Activating Token Index: 287