Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2218 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.7234. Min Act: -0.0000

Data Index: 1507892 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.8245. Min Act: -0.0000

Data Index: 1583243 (Python Code)

Max Activating Token Index: 946

Text #2

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.7399. Min Act: -0.0000

Data Index: 1411014 (Python Code)

Max Activating Token Index: 945

Text #3

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.4476. Min Act: -0.0000

Data Index: 1609517 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2325. Min Act: -0.0000

Data Index: 1446619 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2832. Min Act: -0.0000

Data Index: 1545804 (Python Code)

Max Activating Token Index: 411

Text #6

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2487. Min Act: -0.0000

Data Index: 1386180 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.1749. Min Act: -0.0000

Data Index: 1387809 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2093. Min Act: -0.0000

Data Index: 1506144 (Python Code)

Max Activating Token Index: 226

Text #9

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.2287. Min Act: -0.0000

Data Index: 1556046 (Python Code)

Max Activating Token Index: 111

Text #10

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1429805 (Python Code)

Max Activating Token Index: 739

Text #11

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1517764 (Python Code)

Max Activating Token Index: 284

Text #12

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.1451. Min Act: -0.0000

Data Index: 1515008 (Python Code)

Max Activating Token Index: 60

Text #13

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1438898 (Python Code)

Max Activating Token Index: 755

Text #14

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1376364 (Python Code)

Max Activating Token Index: 609

Text #15

Max Range: 1.8245. Min Range: -1.8245

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1366038 (Python Code)

Max Activating Token Index: 706

Text #16

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.0431. Min Act: -0.0000

Data Index: 1369520 (Python Code)

Max Activating Token Index: 832

Text #17

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1592991 (Python Code)

Max Activating Token Index: 193

Text #18

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1410613 (Python Code)

Max Activating Token Index: 327

Text #19

Max Range: 1.8245. Min Range: -1.8245

Max Act: 1.0768. Min Act: -0.0000

Data Index: 1586571 (Python Code)

Max Activating Token Index: 541