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

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

Neuron 1120 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.3857. Min Range: -8.3857

Max Act: 8.3857. Min Act: -0.0002

Data Index: 1627184 (Python Code)

Max Activating Token Index: 85

Text #1

Max Range: 8.3857. Min Range: -8.3857

Max Act: 7.3030. Min Act: -0.0002

Data Index: 865904 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 8.3857. Min Range: -8.3857

Max Act: 4.1501. Min Act: -0.0002

Data Index: 1322200 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 8.3857. Min Range: -8.3857

Max Act: 3.6228. Min Act: -0.0002

Data Index: 446356 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 8.3857. Min Range: -8.3857

Max Act: 3.4106. Min Act: -0.0002

Data Index: 234828 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 8.3857. Min Range: -8.3857

Max Act: 3.3997. Min Act: -0.0001

Data Index: 195311 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 8.3857. Min Range: -8.3857

Max Act: 3.4519. Min Act: -0.0002

Data Index: 755781 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 8.3857. Min Range: -8.3857

Max Act: 3.2833. Min Act: -0.0002

Data Index: 682745 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 8.3857. Min Range: -8.3857

Max Act: 3.0198. Min Act: -0.0002

Data Index: 130994 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 8.3857. Min Range: -8.3857

Max Act: 3.0842. Min Act: -0.0001

Data Index: 975390 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 8.3857. Min Range: -8.3857

Max Act: 3.0757. Min Act: -0.0002

Data Index: 531848 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 8.3857. Min Range: -8.3857

Max Act: 2.9773. Min Act: -0.0001

Data Index: 1320545 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 8.3857. Min Range: -8.3857

Max Act: 3.1741. Min Act: -0.0002

Data Index: 442423 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 8.3857. Min Range: -8.3857

Max Act: 3.0202. Min Act: -0.0002

Data Index: 1070075 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 8.3857. Min Range: -8.3857

Max Act: 3.0838. Min Act: -0.0001

Data Index: 1148662 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 8.3857. Min Range: -8.3857

Max Act: 2.9123. Min Act: -0.0002

Data Index: 1294899 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 8.3857. Min Range: -8.3857

Max Act: 2.9117. Min Act: -0.0002

Data Index: 827658 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 8.3857. Min Range: -8.3857

Max Act: 2.9434. Min Act: -0.0002

Data Index: 748801 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 8.3857. Min Range: -8.3857

Max Act: 2.7679. Min Act: -0.0002

Data Index: 739927 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 8.3857. Min Range: -8.3857

Max Act: 2.7445. Min Act: -0.0001

Data Index: 1349992 (C4 (Web Text))

Max Activating Token Index: 886