Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 395 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1964. Min Act: -0.0003

Data Index: 1271370 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.2097. Min Act: -0.0003

Data Index: 387786 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1975. Min Act: -0.0003

Data Index: 985320 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1959. Min Act: -0.0004

Data Index: 32236 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1889. Min Act: -0.0003

Data Index: 349730 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1863. Min Act: -0.0003

Data Index: 894493 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1879. Min Act: -0.0003

Data Index: 1229760 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1861. Min Act: -0.0003

Data Index: 527676 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1857. Min Act: -0.0003

Data Index: 96946 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1945. Min Act: -0.0003

Data Index: 83421 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1806. Min Act: -0.0003

Data Index: 1183265 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1787. Min Act: -0.0003

Data Index: 763870 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1654. Min Act: -0.0003

Data Index: 1217079 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1728. Min Act: -0.0003

Data Index: 372911 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1701. Min Act: -0.0003

Data Index: 735815 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1650. Min Act: -0.0003

Data Index: 1196389 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1628. Min Act: -0.0003

Data Index: 1321513 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1655. Min Act: -0.0003

Data Index: 338455 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1713. Min Act: -0.0003

Data Index: 102070 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1619. Min Act: -0.0003

Data Index: 109680 (C4 (Web Text))

Max Activating Token Index: 811