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

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

Neuron 4607 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.2187. Min Act: -0.0001

Data Index: 452506 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.1324. Min Act: -0.0001

Data Index: 444015 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0623. Min Act: -0.0001

Data Index: 691704 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0321. Min Act: -0.0001

Data Index: 1079478 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0827. Min Act: -0.0001

Data Index: 1204135 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0650. Min Act: -0.0001

Data Index: 542314 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9914. Min Act: -0.0001

Data Index: 92062 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9969. Min Act: -0.0001

Data Index: 611742 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9842. Min Act: -0.0001

Data Index: 130355 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9910. Min Act: -0.0001

Data Index: 781357 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0226. Min Act: -0.0001

Data Index: 1342682 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9908. Min Act: -0.0001

Data Index: 901184 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0167. Min Act: -0.0001

Data Index: 36549 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9536. Min Act: -0.0001

Data Index: 1094305 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9580. Min Act: -0.0001

Data Index: 237368 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9982. Min Act: -0.0001

Data Index: 584793 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0125. Min Act: -0.0001

Data Index: 1338291 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9759. Min Act: -0.0001

Data Index: 719152 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9605. Min Act: -0.0001

Data Index: 323200 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9109. Min Act: -0.0001

Data Index: 712140 (C4 (Web Text))

Max Activating Token Index: 256