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

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

Neuron 4389 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1595971 (Python Code)

Max Activating Token Index: 427

Text #1

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.1333. Min Act: -0.0000

Data Index: 313702 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1561076 (Python Code)

Max Activating Token Index: 894

Text #3

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1578014 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.1061. Min Act: -0.0000

Data Index: 484375 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1444919 (Python Code)

Max Activating Token Index: 219

Text #6

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1417302 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1396454 (Python Code)

Max Activating Token Index: 591

Text #8

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1531568 (Python Code)

Max Activating Token Index: 792

Text #9

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1464807 (Python Code)

Max Activating Token Index: 633

Text #10

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0874. Min Act: -0.0000

Data Index: 1429375 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1655970 (Python Code)

Max Activating Token Index: 497

Text #12

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1556932 (Python Code)

Max Activating Token Index: 194

Text #13

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1432528 (Python Code)

Max Activating Token Index: 196

Text #14

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0887. Min Act: -0.0000

Data Index: 90617 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0866. Min Act: -0.0000

Data Index: 137566 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0858. Min Act: -0.0000

Data Index: 98302 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1460752 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1656097 (Python Code)

Max Activating Token Index: 960

Text #19

Max Range: 0.1333. Min Range: -0.1333

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1576687 (Python Code)

Max Activating Token Index: 185