Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4619 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1187. Min Act: -0.0002

Data Index: 651860 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1261475 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1298055 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0925. Min Act: -0.0002

Data Index: 194800 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0917. Min Act: -0.0002

Data Index: 896324 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1118446 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0818. Min Act: -0.0002

Data Index: 70370 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1273869 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0887. Min Act: -0.0002

Data Index: 42766 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1270364 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0785. Min Act: -0.0002

Data Index: 234079 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0776. Min Act: -0.0002

Data Index: 612228 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0745. Min Act: -0.0002

Data Index: 88926 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0741. Min Act: -0.0002

Data Index: 345147 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0726. Min Act: -0.0002

Data Index: 206642 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1166379 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1319680 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1196726 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1338152 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0717. Min Act: -0.0002

Data Index: 515431 (C4 (Web Text))

Max Activating Token Index: 582