Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4933 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.5696. Min Act: -0.0001

Data Index: 1391246 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.5978. Min Act: -0.0001

Data Index: 1403998 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.5958. Min Act: -0.0001

Data Index: 1468741 (Python Code)

Max Activating Token Index: 349

Text #3

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.5343. Min Act: -0.0001

Data Index: 1419945 (Python Code)

Max Activating Token Index: 689

Text #4

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3959. Min Act: -0.0001

Data Index: 1622804 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.4345. Min Act: -0.0001

Data Index: 1392028 (Python Code)

Max Activating Token Index: 758

Text #6

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.5074. Min Act: -0.0001

Data Index: 1360032 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.4687. Min Act: -0.0001

Data Index: 1578624 (Python Code)

Max Activating Token Index: 261

Text #8

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.4741. Min Act: -0.0001

Data Index: 1403418 (Python Code)

Max Activating Token Index: 133

Text #9

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3874. Min Act: -0.0001

Data Index: 1412922 (Python Code)

Max Activating Token Index: 406

Text #10

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.4383. Min Act: -0.0001

Data Index: 1512185 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.4280. Min Act: -0.0001

Data Index: 1604438 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.4663. Min Act: -0.0001

Data Index: 1634765 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.4119. Min Act: -0.0000

Data Index: 1601055 (Python Code)

Max Activating Token Index: 232

Text #14

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3852. Min Act: -0.0001

Data Index: 1498924 (Python Code)

Max Activating Token Index: 323

Text #15

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3833. Min Act: -0.0001

Data Index: 1519186 (Python Code)

Max Activating Token Index: 385

Text #16

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3835. Min Act: -0.0001

Data Index: 1577828 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.4105. Min Act: -0.0000

Data Index: 1598646 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3216. Min Act: -0.0000

Data Index: 1491218 (Python Code)

Max Activating Token Index: 112

Text #19

Max Range: 1.5978. Min Range: -1.5978

Max Act: 1.3838. Min Act: -0.0000

Data Index: 1623950 (Python Code)

Max Activating Token Index: 762