Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1785 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.3017. Min Act: -0.0001

Data Index: 997591 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2610. Min Act: -0.0001

Data Index: 543511 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2529. Min Act: -0.0001

Data Index: 204008 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2047. Min Act: -0.0001

Data Index: 778175 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2171. Min Act: -0.0001

Data Index: 45506 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1964. Min Act: -0.0001

Data Index: 781521 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1930. Min Act: -0.0001

Data Index: 707597 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.2023. Min Act: -0.0001

Data Index: 937391 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1844. Min Act: -0.0001

Data Index: 603359 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1744. Min Act: -0.0001

Data Index: 654093 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1919. Min Act: -0.0001

Data Index: 721281 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1861. Min Act: -0.0001

Data Index: 939352 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1827. Min Act: -0.0001

Data Index: 1053849 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1708. Min Act: -0.0001

Data Index: 1034631 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1768. Min Act: -0.0001

Data Index: 132627 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1603. Min Act: -0.0001

Data Index: 973311 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1789. Min Act: -0.0001

Data Index: 1199641 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1904. Min Act: -0.0001

Data Index: 879242 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1780. Min Act: -0.0001

Data Index: 1075145 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.3017. Min Range: -0.3017

Max Act: 0.1708. Min Act: -0.0001

Data Index: 742548 (C4 (Web Text))

Max Activating Token Index: 274