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

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

Neuron 3686 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: 0.1075. Min Range: -0.1075

Max Act: 0.1075. Min Act: -0.0001

Data Index: 505311 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0918. Min Act: -0.0001

Data Index: 346975 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0909. Min Act: -0.0001

Data Index: 149286 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0879. Min Act: -0.0001

Data Index: 833724 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0923. Min Act: -0.0001

Data Index: 468655 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0889. Min Act: -0.0001

Data Index: 121312 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1061. Min Act: -0.0001

Data Index: 161960 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0822. Min Act: -0.0001

Data Index: 851733 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0853. Min Act: -0.0001

Data Index: 812737 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0820. Min Act: -0.0001

Data Index: 331124 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0834. Min Act: -0.0001

Data Index: 55836 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0832. Min Act: -0.0001

Data Index: 693755 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0775. Min Act: -0.0001

Data Index: 64097 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0771. Min Act: -0.0001

Data Index: 267887 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0772. Min Act: -0.0001

Data Index: 917011 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0715. Min Act: -0.0001

Data Index: 62105 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0800. Min Act: -0.0000

Data Index: 362955 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0716. Min Act: -0.0001

Data Index: 1158757 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1267197 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0710. Min Act: -0.0001

Data Index: 719583 (C4 (Web Text))

Max Activating Token Index: 526