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

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

Neuron 618 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.1187. Min Range: -3.1187

Max Act: 3.1187. Min Act: -0.0000

Data Index: 863436 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.5831. Min Act: -0.0000

Data Index: 633449 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.6914. Min Act: -0.0000

Data Index: 260614 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.1318. Min Act: -0.0000

Data Index: 771 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.3922. Min Act: -0.0000

Data Index: 694614 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.3052. Min Act: -0.0000

Data Index: 889887 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.1739. Min Act: -0.0000

Data Index: 794670 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.2720. Min Act: -0.0000

Data Index: 1116666 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.0200. Min Act: -0.0000

Data Index: 965540 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.1275. Min Act: -0.0000

Data Index: 748678 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.2266. Min Act: -0.0000

Data Index: 99952 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 3.1187. Min Range: -3.1187

Max Act: 1.9565. Min Act: -0.0000

Data Index: 569799 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.0207. Min Act: -0.0000

Data Index: 646357 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 3.1187. Min Range: -3.1187

Max Act: 1.8886. Min Act: -0.0000

Data Index: 1311162 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 3.1187. Min Range: -3.1187

Max Act: 1.9808. Min Act: -0.0000

Data Index: 265941 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.1187. Min Range: -3.1187

Max Act: 1.8616. Min Act: -0.0000

Data Index: 332721 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 3.1187. Min Range: -3.1187

Max Act: 1.9211. Min Act: -0.0000

Data Index: 1174314 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 3.1187. Min Range: -3.1187

Max Act: 1.9263. Min Act: -0.0001

Data Index: 1031055 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 3.1187. Min Range: -3.1187

Max Act: 1.9202. Min Act: -0.0000

Data Index: 113410 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 3.1187. Min Range: -3.1187

Max Act: 2.0157. Min Act: -0.0000

Data Index: 335761 (C4 (Web Text))

Max Activating Token Index: 64