Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1302 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1653. Min Act: -0.0003

Data Index: 416550 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1688. Min Act: -0.0003

Data Index: 342699 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1411. Min Act: -0.0003

Data Index: 851313 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1417. Min Act: -0.0003

Data Index: 1338246 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1399. Min Act: -0.0004

Data Index: 932032 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1444. Min Act: -0.0003

Data Index: 1021543 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1376. Min Act: -0.0003

Data Index: 698041 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1278. Min Act: -0.0003

Data Index: 723325 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1346. Min Act: -0.0003

Data Index: 1600522 (Python Code)

Max Activating Token Index: 681

Text #9

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1261. Min Act: -0.0004

Data Index: 581959 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1307. Min Act: -0.0003

Data Index: 834214 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1316. Min Act: -0.0003

Data Index: 1221758 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1262. Min Act: -0.0004

Data Index: 83217 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1286. Min Act: -0.0004

Data Index: 986856 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1245. Min Act: -0.0003

Data Index: 23610 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1204. Min Act: -0.0003

Data Index: 786590 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1261. Min Act: -0.0003

Data Index: 1067939 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1203. Min Act: -0.0004

Data Index: 1174966 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1263. Min Act: -0.0004

Data Index: 52925 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1184. Min Act: -0.0003

Data Index: 32162 (C4 (Web Text))

Max Activating Token Index: 191