Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1913 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1747. Min Act: -0.0001

Data Index: 966477 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1606. Min Act: -0.0001

Data Index: 1422725 (Python Code)

Max Activating Token Index: 514

Text #2

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1504. Min Act: -0.0001

Data Index: 1419130 (Python Code)

Max Activating Token Index: 690

Text #3

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1189. Min Act: -0.0001

Data Index: 272165 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1470620 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1360466 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1205883 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1601563 (Python Code)

Max Activating Token Index: 833

Text #8

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1295. Min Act: -0.0001

Data Index: 776380 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1535249 (Python Code)

Max Activating Token Index: 464

Text #10

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1376. Min Act: -0.0001

Data Index: 813125 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1451849 (Python Code)

Max Activating Token Index: 491

Text #12

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1600223 (Python Code)

Max Activating Token Index: 663

Text #13

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1492619 (Python Code)

Max Activating Token Index: 486

Text #14

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1417531 (Python Code)

Max Activating Token Index: 705

Text #15

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1566620 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1183. Min Act: -0.0001

Data Index: 15938 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1425739 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1208. Min Act: -0.0001

Data Index: 941631 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.1747. Min Range: -0.1747

Max Act: 0.1297. Min Act: -0.0001

Data Index: 1433016 (Python Code)

Max Activating Token Index: 7