Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3631 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1136. Min Act: -0.0003

Data Index: 744665 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.1048. Min Act: -0.0003

Data Index: 567779 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0948. Min Act: -0.0003

Data Index: 1204400 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0885. Min Act: -0.0003

Data Index: 1029304 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0882. Min Act: -0.0002

Data Index: 721315 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0879. Min Act: -0.0002

Data Index: 625119 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1548571 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0817. Min Act: -0.0003

Data Index: 1277670 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0849. Min Act: -0.0003

Data Index: 79874 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1636724 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1226288 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1418703 (Python Code)

Max Activating Token Index: 804

Text #12

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0788. Min Act: -0.0003

Data Index: 1498152 (Python Code)

Max Activating Token Index: 480

Text #13

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1403695 (Python Code)

Max Activating Token Index: 742

Text #14

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1097894 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0706. Min Act: -0.0002

Data Index: 877441 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0731. Min Act: -0.0003

Data Index: 940292 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0716. Min Act: -0.0002

Data Index: 75447 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1548637 (Python Code)

Max Activating Token Index: 694

Text #19

Max Range: 0.1136. Min Range: -0.1136

Max Act: 0.0704. Min Act: -0.0003

Data Index: 177223 (C4 (Web Text))

Max Activating Token Index: 129