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

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

Neuron 3679 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: 0.1354. Min Range: -0.1354

Max Act: 0.1354. Min Act: -0.0002

Data Index: 1206824 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1133. Min Act: -0.0002

Data Index: 548147 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1114. Min Act: -0.0002

Data Index: 338799 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.1004. Min Act: -0.0002

Data Index: 922054 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0955. Min Act: -0.0002

Data Index: 306301 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0847. Min Act: -0.0002

Data Index: 106143 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0846. Min Act: -0.0002

Data Index: 858645 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1012259 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1168193 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0895. Min Act: -0.0002

Data Index: 361465 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0830. Min Act: -0.0002

Data Index: 593989 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0834. Min Act: -0.0002

Data Index: 30008 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1348392 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1175482 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1304970 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0731. Min Act: -0.0003

Data Index: 1117944 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0798. Min Act: -0.0002

Data Index: 167202 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0777. Min Act: -0.0002

Data Index: 643435 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0782. Min Act: -0.0002

Data Index: 193600 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.1354. Min Range: -0.1354

Max Act: 0.0771. Min Act: -0.0002

Data Index: 78619 (C4 (Web Text))

Max Activating Token Index: 604