Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5068 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1628. Min Act: -0.0002

Data Index: 807458 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1520. Min Act: -0.0002

Data Index: 820502 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1499. Min Act: -0.0002

Data Index: 538609 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1467. Min Act: -0.0002

Data Index: 813254 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1374. Min Act: -0.0002

Data Index: 438317 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1320. Min Act: -0.0002

Data Index: 1169687 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1383. Min Act: -0.0002

Data Index: 1058744 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1197382 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1335. Min Act: -0.0002

Data Index: 216266 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1339. Min Act: -0.0002

Data Index: 1279975 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1317. Min Act: -0.0002

Data Index: 149715 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1314. Min Act: -0.0002

Data Index: 657811 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1295. Min Act: -0.0002

Data Index: 1187627 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1283. Min Act: -0.0002

Data Index: 1258735 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1252. Min Act: -0.0002

Data Index: 43417 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1284. Min Act: -0.0002

Data Index: 869771 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1258. Min Act: -0.0002

Data Index: 634771 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1257. Min Act: -0.0002

Data Index: 344488 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1264. Min Act: -0.0002

Data Index: 820824 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1253. Min Act: -0.0002

Data Index: 532927 (C4 (Web Text))

Max Activating Token Index: 785