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

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

Neuron 3509 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.1293. Min Act: -0.0003

Data Index: 1334619 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0927. Min Act: -0.0003

Data Index: 1521930 (Python Code)

Max Activating Token Index: 641

Text #2

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0555. Min Act: -0.0003

Data Index: 1492295 (Python Code)

Max Activating Token Index: 849

Text #3

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1020910 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1652188 (Python Code)

Max Activating Token Index: 451

Text #5

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1647831 (Python Code)

Max Activating Token Index: 690

Text #6

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0421. Min Act: -0.0003

Data Index: 734353 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1160832 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0376. Min Act: -0.0004

Data Index: 969234 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0375. Min Act: -0.0003

Data Index: 270469 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1051990 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0354. Min Act: -0.0003

Data Index: 888200 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0375. Min Act: -0.0003

Data Index: 734711 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1604509 (Python Code)

Max Activating Token Index: 996

Text #14

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0340. Min Act: -0.0004

Data Index: 863813 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1307631 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1611362 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0333. Min Act: -0.0003

Data Index: 20713 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0322. Min Act: -0.0003

Data Index: 662285 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.1293. Min Range: -0.1293

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1569892 (Python Code)

Max Activating Token Index: 918