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

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

Neuron 1566 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1649337 (Python Code)

Max Activating Token Index: 765

Text #1

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1580087 (Python Code)

Max Activating Token Index: 175

Text #2

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1453. Min Act: -0.0001

Data Index: 1622328 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1364. Min Act: -0.0001

Data Index: 155490 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1421. Min Act: -0.0001

Data Index: 1421394 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1372. Min Act: -0.0001

Data Index: 1458858 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1313. Min Act: -0.0001

Data Index: 975984 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1538323 (Python Code)

Max Activating Token Index: 233

Text #8

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1369. Min Act: -0.0001

Data Index: 1368829 (Python Code)

Max Activating Token Index: 401

Text #9

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1407304 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1539458 (Python Code)

Max Activating Token Index: 783

Text #11

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1324. Min Act: -0.0001

Data Index: 1604740 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1331. Min Act: -0.0001

Data Index: 1441260 (Python Code)

Max Activating Token Index: 70

Text #13

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1376245 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1272. Min Act: -0.0001

Data Index: 1418342 (Python Code)

Max Activating Token Index: 474

Text #15

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1454528 (Python Code)

Max Activating Token Index: 559

Text #16

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1546511 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1259. Min Act: -0.0001

Data Index: 1656183 (Python Code)

Max Activating Token Index: 744

Text #18

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1386762 (Python Code)

Max Activating Token Index: 360

Text #19

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1385721 (Python Code)

Max Activating Token Index: 1000