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

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

Neuron 2642 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.5218. Min Act: -0.0000

Data Index: 158809 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.4920. Min Act: -0.0000

Data Index: 647000 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.4308. Min Act: -0.0000

Data Index: 743288 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.2397. Min Act: -0.0000

Data Index: 486660 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.1791. Min Act: -0.0000

Data Index: 598475 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0729. Min Act: -0.0000

Data Index: 981315 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0914. Min Act: -0.0000

Data Index: 763496 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0952. Min Act: -0.0000

Data Index: 610816 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0267. Min Act: -0.0000

Data Index: 389644 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0125. Min Act: -0.0000

Data Index: 1328550 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0892. Min Act: -0.0000

Data Index: 200673 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0223. Min Act: -0.0000

Data Index: 376365 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0230. Min Act: -0.0000

Data Index: 152513 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0519. Min Act: -0.0000

Data Index: 58659 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0536. Min Act: -0.0000

Data Index: 1304858 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1241186 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0190. Min Act: -0.0000

Data Index: 616478 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0130. Min Act: -0.0000

Data Index: 1068251 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0451. Min Act: -0.0000

Data Index: 606339 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 1.5218. Min Range: -1.5218

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1417535 (Python Code)

Max Activating Token Index: 499