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

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

Neuron 4750 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.2298. Min Act: -0.0002

Data Index: 58690 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1609. Min Act: -0.0002

Data Index: 510124 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1704. Min Act: -0.0002

Data Index: 346878 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1813. Min Act: -0.0002

Data Index: 106460 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1537. Min Act: -0.0002

Data Index: 687541 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1644. Min Act: -0.0002

Data Index: 539193 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1700. Min Act: -0.0002

Data Index: 1327056 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1565. Min Act: -0.0002

Data Index: 135887 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1662. Min Act: -0.0002

Data Index: 992898 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1643. Min Act: -0.0002

Data Index: 1244879 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1612. Min Act: -0.0002

Data Index: 1054099 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1606. Min Act: -0.0002

Data Index: 189643 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1449. Min Act: -0.0002

Data Index: 967534 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1739. Min Act: -0.0002

Data Index: 162851 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1389. Min Act: -0.0002

Data Index: 905222 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1553. Min Act: -0.0002

Data Index: 97294 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1554. Min Act: -0.0002

Data Index: 768361 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1541. Min Act: -0.0002

Data Index: 454842 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1451. Min Act: -0.0002

Data Index: 1084431 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1493. Min Act: -0.0002

Data Index: 325038 (C4 (Web Text))

Max Activating Token Index: 561