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

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

Neuron 3841 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1368607 (Python Code)

Max Activating Token Index: 527

Text #1

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1495133 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1459238 (Python Code)

Max Activating Token Index: 43

Text #3

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1600240 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1464. Min Act: -0.0000

Data Index: 1402112 (Python Code)

Max Activating Token Index: 355

Text #5

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1385025 (Python Code)

Max Activating Token Index: 268

Text #6

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1442211 (Python Code)

Max Activating Token Index: 43

Text #7

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1472120 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1412063 (Python Code)

Max Activating Token Index: 130

Text #9

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1417705 (Python Code)

Max Activating Token Index: 635

Text #10

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1515419 (Python Code)

Max Activating Token Index: 574

Text #11

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1569710 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1584288 (Python Code)

Max Activating Token Index: 551

Text #13

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1368282 (Python Code)

Max Activating Token Index: 336

Text #14

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1491152 (Python Code)

Max Activating Token Index: 61

Text #15

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1428916 (Python Code)

Max Activating Token Index: 679

Text #16

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1591096 (Python Code)

Max Activating Token Index: 597

Text #17

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1501270 (Python Code)

Max Activating Token Index: 355

Text #18

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1439216 (Python Code)

Max Activating Token Index: 321

Text #19

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1190. Min Act: -0.0001

Data Index: 176155 (C4 (Web Text))

Max Activating Token Index: 535