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

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

Neuron 1565 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: 0.1717. Min Range: -0.1717

Max Act: 0.1691. Min Act: -0.0002

Data Index: 573718 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1717. Min Act: -0.0002

Data Index: 974666 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1666. Min Act: -0.0002

Data Index: 129222 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1500. Min Act: -0.0002

Data Index: 1088604 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1497. Min Act: -0.0002

Data Index: 389177 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1380. Min Act: -0.0002

Data Index: 1336488 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1422. Min Act: -0.0002

Data Index: 545940 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1406. Min Act: -0.0002

Data Index: 274651 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1345. Min Act: -0.0002

Data Index: 147145 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1392. Min Act: -0.0002

Data Index: 20453 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1315. Min Act: -0.0002

Data Index: 124438 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1360. Min Act: -0.0002

Data Index: 70637 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1215. Min Act: -0.0002

Data Index: 806470 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1380. Min Act: -0.0002

Data Index: 221756 (C4 (Web Text))

Max Activating Token Index: 799

Text #14

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1276. Min Act: -0.0002

Data Index: 497858 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1356. Min Act: -0.0002

Data Index: 975212 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1271. Min Act: -0.0002

Data Index: 886914 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1237. Min Act: -0.0002

Data Index: 390750 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1244. Min Act: -0.0002

Data Index: 291371 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1322267 (C4 (Web Text))

Max Activating Token Index: 631