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

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

Neuron 4567 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1792. Min Act: -0.0001

Data Index: 1586891 (Python Code)

Max Activating Token Index: 315

Text #1

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1702. Min Act: -0.0001

Data Index: 1433937 (Python Code)

Max Activating Token Index: 667

Text #2

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1616074 (Python Code)

Max Activating Token Index: 505

Text #3

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1503. Min Act: -0.0001

Data Index: 1458016 (Python Code)

Max Activating Token Index: 128

Text #4

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1386129 (Python Code)

Max Activating Token Index: 238

Text #5

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1539124 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1387671 (Python Code)

Max Activating Token Index: 766

Text #7

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1536586 (Python Code)

Max Activating Token Index: 145

Text #8

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1650055 (Python Code)

Max Activating Token Index: 827

Text #9

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1493998 (Python Code)

Max Activating Token Index: 390

Text #10

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1552468 (Python Code)

Max Activating Token Index: 423

Text #11

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1318. Min Act: -0.0001

Data Index: 1444654 (Python Code)

Max Activating Token Index: 117

Text #12

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1568393 (Python Code)

Max Activating Token Index: 489

Text #13

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1620989 (Python Code)

Max Activating Token Index: 252

Text #14

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1448589 (Python Code)

Max Activating Token Index: 709

Text #15

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1491144 (Python Code)

Max Activating Token Index: 278

Text #16

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1460329 (Python Code)

Max Activating Token Index: 802

Text #17

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1548796 (Python Code)

Max Activating Token Index: 771

Text #18

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1525371 (Python Code)

Max Activating Token Index: 167

Text #19

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1555843 (Python Code)

Max Activating Token Index: 161