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

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

Neuron 289 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.9562. Min Act: -0.0001

Data Index: 571689 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.9033. Min Act: -0.0001

Data Index: 768803 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.9728. Min Act: -0.0001

Data Index: 769389 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.9183. Min Act: -0.0001

Data Index: 618996 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.9051. Min Act: -0.0001

Data Index: 634245 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8898. Min Act: -0.0001

Data Index: 667762 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8714. Min Act: -0.0001

Data Index: 1017473 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8486. Min Act: -0.0001

Data Index: 1205483 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8364. Min Act: -0.0001

Data Index: 542846 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8655. Min Act: -0.0001

Data Index: 14954 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8774. Min Act: -0.0001

Data Index: 134097 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8980. Min Act: -0.0001

Data Index: 820428 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8871. Min Act: -0.0001

Data Index: 690841 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8913. Min Act: -0.0001

Data Index: 866908 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.9006. Min Act: -0.0001

Data Index: 312679 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8932. Min Act: -0.0001

Data Index: 394648 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8432. Min Act: -0.0001

Data Index: 960911 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8560. Min Act: -0.0001

Data Index: 374011 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8210. Min Act: -0.0001

Data Index: 285523 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.9728. Min Range: -0.9728

Max Act: 0.8684. Min Act: -0.0001

Data Index: 1120017 (C4 (Web Text))

Max Activating Token Index: 49