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

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

Neuron 5070 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.4230. Min Act: -0.0000

Data Index: 1535864 (Python Code)

Max Activating Token Index: 337

Text #1

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.5664. Min Act: -0.0000

Data Index: 1411935 (Python Code)

Max Activating Token Index: 330

Text #2

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.5678. Min Act: -0.0000

Data Index: 1409156 (Python Code)

Max Activating Token Index: 381

Text #3

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.2226. Min Act: -0.0000

Data Index: 1411893 (Python Code)

Max Activating Token Index: 383

Text #4

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.1639. Min Act: -0.0000

Data Index: 1582974 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.3367. Min Act: -0.0000

Data Index: 1638605 (Python Code)

Max Activating Token Index: 499

Text #6

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.1164. Min Act: -0.0000

Data Index: 1390159 (Python Code)

Max Activating Token Index: 79

Text #7

Max Range: 4.5678. Min Range: -4.5678

Max Act: 3.8972. Min Act: -0.0000

Data Index: 1607414 (Python Code)

Max Activating Token Index: 83

Text #8

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.2185. Min Act: -0.0000

Data Index: 1647662 (Python Code)

Max Activating Token Index: 734

Text #9

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.0401. Min Act: -0.0000

Data Index: 1445505 (Python Code)

Max Activating Token Index: 271

Text #10

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.1702. Min Act: -0.0000

Data Index: 1468243 (Python Code)

Max Activating Token Index: 767

Text #11

Max Range: 4.5678. Min Range: -4.5678

Max Act: 3.8407. Min Act: -0.0000

Data Index: 1428746 (Python Code)

Max Activating Token Index: 558

Text #12

Max Range: 4.5678. Min Range: -4.5678

Max Act: 3.9914. Min Act: -0.0000

Data Index: 1651770 (Python Code)

Max Activating Token Index: 735

Text #13

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.1428. Min Act: -0.0000

Data Index: 1584629 (Python Code)

Max Activating Token Index: 804

Text #14

Max Range: 4.5678. Min Range: -4.5678

Max Act: 3.9587. Min Act: -0.0000

Data Index: 1537755 (Python Code)

Max Activating Token Index: 281

Text #15

Max Range: 4.5678. Min Range: -4.5678

Max Act: 3.5813. Min Act: -0.0000

Data Index: 1408270 (Python Code)

Max Activating Token Index: 791

Text #16

Max Range: 4.5678. Min Range: -4.5678

Max Act: 3.8546. Min Act: -0.0000

Data Index: 1386735 (Python Code)

Max Activating Token Index: 118

Text #17

Max Range: 4.5678. Min Range: -4.5678

Max Act: 3.8547. Min Act: -0.0000

Data Index: 1645460 (Python Code)

Max Activating Token Index: 130

Text #18

Max Range: 4.5678. Min Range: -4.5678

Max Act: 3.6708. Min Act: -0.0000

Data Index: 1431185 (Python Code)

Max Activating Token Index: 314

Text #19

Max Range: 4.5678. Min Range: -4.5678

Max Act: 4.0133. Min Act: -0.0000

Data Index: 1451977 (Python Code)

Max Activating Token Index: 177