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

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

Neuron 2146 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: 0.8355. Min Range: -0.8355

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1449570 (Python Code)

Max Activating Token Index: 120

Text #1

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7676. Min Act: -0.0001

Data Index: 1614475 (Python Code)

Max Activating Token Index: 595

Text #2

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7106. Min Act: -0.0001

Data Index: 1381027 (Python Code)

Max Activating Token Index: 283

Text #3

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7010. Min Act: -0.0001

Data Index: 1543260 (Python Code)

Max Activating Token Index: 556

Text #4

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7214. Min Act: -0.0000

Data Index: 1462708 (Python Code)

Max Activating Token Index: 146

Text #5

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1501905 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7268. Min Act: -0.0001

Data Index: 1403584 (Python Code)

Max Activating Token Index: 427

Text #7

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6777. Min Act: -0.0001

Data Index: 1540939 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6562. Min Act: -0.0001

Data Index: 1618268 (Python Code)

Max Activating Token Index: 78

Text #9

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.7097. Min Act: -0.0001

Data Index: 1471108 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1419511 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6435. Min Act: -0.0001

Data Index: 1493764 (Python Code)

Max Activating Token Index: 534

Text #12

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6581. Min Act: -0.0001

Data Index: 1647327 (Python Code)

Max Activating Token Index: 609

Text #13

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6352. Min Act: -0.0001

Data Index: 1453218 (Python Code)

Max Activating Token Index: 234

Text #14

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6218. Min Act: -0.0001

Data Index: 1553032 (Python Code)

Max Activating Token Index: 969

Text #15

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6419. Min Act: -0.0001

Data Index: 1482904 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6180. Min Act: -0.0001

Data Index: 1430302 (Python Code)

Max Activating Token Index: 908

Text #17

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6427. Min Act: -0.0001

Data Index: 1469115 (Python Code)

Max Activating Token Index: 1017

Text #18

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.5844. Min Act: -0.0001

Data Index: 1486129 (Python Code)

Max Activating Token Index: 912

Text #19

Max Range: 0.8355. Min Range: -0.8355

Max Act: 0.6550. Min Act: -0.0001

Data Index: 1639668 (Python Code)

Max Activating Token Index: 611