Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3887 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0002

Data Index: 18679 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0411. Min Act: -0.0001

Data Index: 763270 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0479. Min Act: -0.0001

Data Index: 777024 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1177727 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0464. Min Act: -0.0002

Data Index: 57670 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0458. Min Act: -0.0002

Data Index: 32322 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0453. Min Act: -0.0002

Data Index: 669835 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0442. Min Act: -0.0002

Data Index: 759351 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0442. Min Act: -0.0001

Data Index: 867336 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0438. Min Act: -0.0002

Data Index: 49534 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0423. Min Act: -0.0001

Data Index: 460765 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1193310 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1056174 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1292345 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0434. Min Act: -0.0001

Data Index: 877067 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0424. Min Act: -0.0002

Data Index: 871267 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0411. Min Act: -0.0001

Data Index: 973202 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0397. Min Act: -0.0001

Data Index: 847126 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0431. Min Act: -0.0001

Data Index: 272771 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1059664 (C4 (Web Text))

Max Activating Token Index: 272