Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 285 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1891. Min Act: -0.0002

Data Index: 207313 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1519. Min Act: -0.0002

Data Index: 1290450 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1490. Min Act: -0.0002

Data Index: 241242 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1601. Min Act: -0.0002

Data Index: 801541 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1386. Min Act: -0.0002

Data Index: 280941 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1308. Min Act: -0.0002

Data Index: 984676 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1017909 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1289. Min Act: -0.0002

Data Index: 70630 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1226. Min Act: -0.0002

Data Index: 172829 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1204. Min Act: -0.0002

Data Index: 359471 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1295. Min Act: -0.0002

Data Index: 1230651 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1241. Min Act: -0.0002

Data Index: 1270861 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1227. Min Act: -0.0001

Data Index: 788561 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1410. Min Act: -0.0002

Data Index: 809430 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1196. Min Act: -0.0002

Data Index: 233115 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1286647 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1182. Min Act: -0.0001

Data Index: 383503 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1156. Min Act: -0.0001

Data Index: 814851 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1120. Min Act: -0.0002

Data Index: 944910 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1184. Min Act: -0.0001

Data Index: 798839 (C4 (Web Text))

Max Activating Token Index: 1001