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

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

Neuron 4859 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: 0.2502. Min Range: -0.2502

Max Act: 0.2502. Min Act: -0.0002

Data Index: 1148212 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2018. Min Act: -0.0002

Data Index: 64995 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1862. Min Act: -0.0002

Data Index: 1164600 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1824. Min Act: -0.0002

Data Index: 130369 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1634. Min Act: -0.0002

Data Index: 300320 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1762. Min Act: -0.0002

Data Index: 727990 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1782. Min Act: -0.0002

Data Index: 554865 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1789. Min Act: -0.0002

Data Index: 1346558 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1787. Min Act: -0.0002

Data Index: 197113 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1863. Min Act: -0.0002

Data Index: 1140570 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1899. Min Act: -0.0002

Data Index: 141953 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1866. Min Act: -0.0002

Data Index: 711308 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1704. Min Act: -0.0002

Data Index: 783695 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1872. Min Act: -0.0002

Data Index: 1262009 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2112. Min Act: -0.0002

Data Index: 941871 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1722. Min Act: -0.0002

Data Index: 198495 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1393. Min Act: -0.0002

Data Index: 1352912 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1631. Min Act: -0.0002

Data Index: 973450 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1737. Min Act: -0.0002

Data Index: 390010 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1572. Min Act: -0.0002

Data Index: 1202046 (C4 (Web Text))

Max Activating Token Index: 289