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

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

Neuron 3578 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: 0.1238. Min Range: -0.1238

Max Act: 0.1238. Min Act: -0.0002

Data Index: 1064043 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1033. Min Act: -0.0002

Data Index: 775557 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1181163 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0990. Min Act: -0.0002

Data Index: 969901 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0887. Min Act: -0.0002

Data Index: 972341 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0993. Min Act: -0.0002

Data Index: 719572 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1012186 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0849. Min Act: -0.0002

Data Index: 997502 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1162333 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0864. Min Act: -0.0002

Data Index: 145100 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1198404 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0791. Min Act: -0.0002

Data Index: 779118 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0858. Min Act: -0.0002

Data Index: 812251 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0770. Min Act: -0.0002

Data Index: 266382 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0752. Min Act: -0.0002

Data Index: 261073 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0679. Min Act: -0.0002

Data Index: 32445 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0868. Min Act: -0.0002

Data Index: 857046 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1083998 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0925. Min Act: -0.0002

Data Index: 542260 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0801. Min Act: -0.0002

Data Index: 90702 (C4 (Web Text))

Max Activating Token Index: 743