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

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

Neuron 5978 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8461. Min Act: -0.0001

Data Index: 1634620 (Python Code)

Max Activating Token Index: 185

Text #1

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8246. Min Act: -0.0001

Data Index: 1502983 (Python Code)

Max Activating Token Index: 111

Text #2

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.8330. Min Act: -0.0001

Data Index: 1487153 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7664. Min Act: -0.0001

Data Index: 1599535 (Python Code)

Max Activating Token Index: 148

Text #4

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7243. Min Act: -0.0001

Data Index: 1481791 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7364. Min Act: -0.0001

Data Index: 1424433 (Python Code)

Max Activating Token Index: 696

Text #6

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7499. Min Act: -0.0001

Data Index: 1653855 (Python Code)

Max Activating Token Index: 753

Text #7

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7496. Min Act: -0.0001

Data Index: 1634067 (Python Code)

Max Activating Token Index: 119

Text #8

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7234. Min Act: -0.0001

Data Index: 1587950 (Python Code)

Max Activating Token Index: 145

Text #9

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7423. Min Act: -0.0001

Data Index: 1564122 (Python Code)

Max Activating Token Index: 456

Text #10

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6936. Min Act: -0.0001

Data Index: 1456193 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6719. Min Act: -0.0001

Data Index: 1462332 (Python Code)

Max Activating Token Index: 240

Text #12

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7121. Min Act: -0.0001

Data Index: 1569840 (Python Code)

Max Activating Token Index: 725

Text #13

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7461. Min Act: -0.0001

Data Index: 1384504 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7511. Min Act: -0.0001

Data Index: 1622095 (Python Code)

Max Activating Token Index: 283

Text #15

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6877. Min Act: -0.0001

Data Index: 1386575 (Python Code)

Max Activating Token Index: 289

Text #16

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.7215. Min Act: -0.0001

Data Index: 1539643 (Python Code)

Max Activating Token Index: 1008

Text #17

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6905. Min Act: -0.0001

Data Index: 1377301 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6664. Min Act: -0.0001

Data Index: 1614880 (Python Code)

Max Activating Token Index: 246

Text #19

Max Range: 0.8461. Min Range: -0.8461

Max Act: 0.6313. Min Act: -0.0001

Data Index: 1372834 (Python Code)

Max Activating Token Index: 141