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

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

Neuron 1623 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: 0.2120. Min Range: -0.2120

Max Act: 0.2106. Min Act: -0.0002

Data Index: 1587273 (Python Code)

Max Activating Token Index: 319

Text #1

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1958. Min Act: -0.0002

Data Index: 1391613 (Python Code)

Max Activating Token Index: 476

Text #2

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1999. Min Act: -0.0002

Data Index: 1362763 (Python Code)

Max Activating Token Index: 141

Text #3

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2103. Min Act: -0.0002

Data Index: 1480671 (Python Code)

Max Activating Token Index: 180

Text #4

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2104. Min Act: -0.0002

Data Index: 1614245 (Python Code)

Max Activating Token Index: 58

Text #5

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1959. Min Act: -0.0002

Data Index: 1634341 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1909. Min Act: -0.0002

Data Index: 1614504 (Python Code)

Max Activating Token Index: 545

Text #7

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2036. Min Act: -0.0002

Data Index: 1435895 (Python Code)

Max Activating Token Index: 949

Text #8

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1795. Min Act: -0.0002

Data Index: 1546918 (Python Code)

Max Activating Token Index: 687

Text #9

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1891. Min Act: -0.0002

Data Index: 1419938 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2120. Min Act: -0.0002

Data Index: 1412403 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1829. Min Act: -0.0002

Data Index: 27172 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1890. Min Act: -0.0002

Data Index: 1574974 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2119. Min Act: -0.0002

Data Index: 1577932 (Python Code)

Max Activating Token Index: 417

Text #14

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1755. Min Act: -0.0002

Data Index: 1492700 (Python Code)

Max Activating Token Index: 273

Text #15

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1738. Min Act: -0.0002

Data Index: 1380698 (Python Code)

Max Activating Token Index: 782

Text #16

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1788. Min Act: -0.0002

Data Index: 518635 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1979. Min Act: -0.0002

Data Index: 1518536 (Python Code)

Max Activating Token Index: 430

Text #18

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.2038. Min Act: -0.0002

Data Index: 1530536 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 0.2120. Min Range: -0.2120

Max Act: 0.1605. Min Act: -0.0002

Data Index: 1475370 (Python Code)

Max Activating Token Index: 103