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

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

Neuron 1854 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.6462. Min Act: -0.0001

Data Index: 1386897 (Python Code)

Max Activating Token Index: 190

Text #1

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5920. Min Act: -0.0001

Data Index: 1416979 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5972. Min Act: -0.0001

Data Index: 1377807 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.6336. Min Act: -0.0001

Data Index: 1643720 (Python Code)

Max Activating Token Index: 494

Text #4

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.6208. Min Act: -0.0001

Data Index: 1372699 (Python Code)

Max Activating Token Index: 508

Text #5

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5958. Min Act: -0.0001

Data Index: 1493675 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5849. Min Act: -0.0001

Data Index: 1369989 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5644. Min Act: -0.0001

Data Index: 1548662 (Python Code)

Max Activating Token Index: 571

Text #8

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5453. Min Act: -0.0001

Data Index: 1366739 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5350. Min Act: -0.0001

Data Index: 1443294 (Python Code)

Max Activating Token Index: 128

Text #10

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5334. Min Act: -0.0001

Data Index: 1390835 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5233. Min Act: -0.0001

Data Index: 1442528 (Python Code)

Max Activating Token Index: 244

Text #12

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5424. Min Act: -0.0001

Data Index: 1494782 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5291. Min Act: -0.0001

Data Index: 1363986 (Python Code)

Max Activating Token Index: 289

Text #14

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5427. Min Act: -0.0001

Data Index: 1387432 (Python Code)

Max Activating Token Index: 243

Text #15

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5371. Min Act: -0.0001

Data Index: 1553205 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5415. Min Act: -0.0001

Data Index: 1488389 (Python Code)

Max Activating Token Index: 132

Text #17

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.6125. Min Act: -0.0001

Data Index: 1566616 (Python Code)

Max Activating Token Index: 666

Text #18

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5211. Min Act: -0.0001

Data Index: 1636981 (Python Code)

Max Activating Token Index: 313

Text #19

Max Range: 0.6462. Min Range: -0.6462

Max Act: 0.5103. Min Act: -0.0001

Data Index: 1472195 (Python Code)

Max Activating Token Index: 66