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

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

Neuron 1844 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: 1.1627. Min Range: -1.1627

Max Act: 1.1607. Min Act: -0.0002

Data Index: 202181 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0618. Min Act: -0.0002

Data Index: 1176830 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.1627. Min Act: -0.0002

Data Index: 780158 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0763. Min Act: -0.0002

Data Index: 940838 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.1033. Min Act: -0.0002

Data Index: 430296 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0554. Min Act: -0.0002

Data Index: 1000901 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0515. Min Act: -0.0002

Data Index: 261584 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.1060. Min Act: -0.0002

Data Index: 749210 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0357. Min Act: -0.0002

Data Index: 1103073 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 1.1627. Min Range: -1.1627

Max Act: 1.0176. Min Act: -0.0002

Data Index: 735264 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9876. Min Act: -0.0002

Data Index: 752521 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9800. Min Act: -0.0002

Data Index: 23839 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9543. Min Act: -0.0002

Data Index: 503019 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9837. Min Act: -0.0002

Data Index: 1016881 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8864. Min Act: -0.0002

Data Index: 669842 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8855. Min Act: -0.0002

Data Index: 1263362 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8725. Min Act: -0.0002

Data Index: 850167 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9078. Min Act: -0.0002

Data Index: 559552 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.8563. Min Act: -0.0002

Data Index: 628071 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.1627. Min Range: -1.1627

Max Act: 0.9343. Min Act: -0.0002

Data Index: 423432 (C4 (Web Text))

Max Activating Token Index: 929