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

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

Neuron 1003 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.8527. Min Act: -0.0001

Data Index: 1339406 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.7175. Min Act: -0.0001

Data Index: 666623 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6174. Min Act: -0.0001

Data Index: 1224012 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6880. Min Act: -0.0001

Data Index: 459936 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6213. Min Act: -0.0001

Data Index: 632173 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6397. Min Act: -0.0001

Data Index: 1153414 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6408. Min Act: -0.0001

Data Index: 185470 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6182. Min Act: -0.0001

Data Index: 321769 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6303. Min Act: -0.0001

Data Index: 1002503 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6021. Min Act: -0.0001

Data Index: 1120887 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6128. Min Act: -0.0001

Data Index: 757290 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6288. Min Act: -0.0001

Data Index: 757274 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6121. Min Act: -0.0001

Data Index: 711809 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6000. Min Act: -0.0001

Data Index: 330273 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6295. Min Act: -0.0001

Data Index: 749700 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5885. Min Act: -0.0001

Data Index: 697709 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5591. Min Act: -0.0001

Data Index: 965201 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5530. Min Act: -0.0001

Data Index: 1075109 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.5663. Min Act: -0.0001

Data Index: 519753 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.8527. Min Range: -0.8527

Max Act: 0.6048. Min Act: -0.0001

Data Index: 936144 (C4 (Web Text))

Max Activating Token Index: 756