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

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

Neuron 1765 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: 0.2178. Min Range: -0.2178

Max Act: 0.2178. Min Act: -0.0002

Data Index: 561493 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1896. Min Act: -0.0002

Data Index: 295117 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1829. Min Act: -0.0002

Data Index: 956368 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1703. Min Act: -0.0002

Data Index: 20662 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1647. Min Act: -0.0002

Data Index: 930905 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1234366 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1574. Min Act: -0.0002

Data Index: 844242 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1690. Min Act: -0.0002

Data Index: 905569 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1570. Min Act: -0.0002

Data Index: 160298 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1391. Min Act: -0.0002

Data Index: 1346204 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1563. Min Act: -0.0002

Data Index: 1298641 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1527. Min Act: -0.0002

Data Index: 913870 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1576. Min Act: -0.0002

Data Index: 1310721 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1584. Min Act: -0.0002

Data Index: 1324891 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1507. Min Act: -0.0002

Data Index: 155704 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1463. Min Act: -0.0002

Data Index: 1038326 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1409. Min Act: -0.0002

Data Index: 1100894 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1427. Min Act: -0.0002

Data Index: 879242 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1422. Min Act: -0.0002

Data Index: 1039915 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.2178. Min Range: -0.2178

Max Act: 0.1569. Min Act: -0.0001

Data Index: 77950 (C4 (Web Text))

Max Activating Token Index: 613