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

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

Neuron 1795 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.7323. Min Act: 0.0001

Data Index: 1405941 (Python Code)

Max Activating Token Index: 860

Text #1

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.6054. Min Act: 0.0000

Data Index: 1424295 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.6067. Min Act: 0.0001

Data Index: 1620740 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.6490. Min Act: 0.0002

Data Index: 1453009 (Python Code)

Max Activating Token Index: 783

Text #4

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5842. Min Act: 0.0002

Data Index: 1561464 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5752. Min Act: 0.0000

Data Index: 1413007 (Python Code)

Max Activating Token Index: 175

Text #6

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5674. Min Act: 0.0000

Data Index: 1527829 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5290. Min Act: 0.0002

Data Index: 1534829 (Python Code)

Max Activating Token Index: 435

Text #8

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4967. Min Act: 0.0002

Data Index: 1574454 (Python Code)

Max Activating Token Index: 232

Text #9

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5141. Min Act: 0.0002

Data Index: 1487684 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5148. Min Act: 0.0002

Data Index: 1441742 (Python Code)

Max Activating Token Index: 354

Text #11

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5271. Min Act: 0.0000

Data Index: 1552181 (Python Code)

Max Activating Token Index: 177

Text #12

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5250. Min Act: 0.0002

Data Index: 1419097 (Python Code)

Max Activating Token Index: 980

Text #13

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4869. Min Act: 0.0001

Data Index: 1616991 (Python Code)

Max Activating Token Index: 267

Text #14

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4923. Min Act: 0.0002

Data Index: 1434851 (Python Code)

Max Activating Token Index: 499

Text #15

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4868. Min Act: 0.0000

Data Index: 1649172 (Python Code)

Max Activating Token Index: 272

Text #16

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1500660 (Python Code)

Max Activating Token Index: 352

Text #17

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4862. Min Act: 0.0000

Data Index: 1561950 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.5055. Min Act: 0.0002

Data Index: 1366419 (Python Code)

Max Activating Token Index: 189

Text #19

Max Range: 0.7323. Min Range: -0.7323

Max Act: 0.4806. Min Act: 0.0001

Data Index: 1442962 (Python Code)

Max Activating Token Index: 592