Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2639 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1402902 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.6235. Min Act: -0.0001

Data Index: 1401738 (Python Code)

Max Activating Token Index: 843

Text #2

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5963. Min Act: -0.0001

Data Index: 1545862 (Python Code)

Max Activating Token Index: 229

Text #3

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5968. Min Act: -0.0001

Data Index: 1492921 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1469839 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5501. Min Act: -0.0001

Data Index: 1653402 (Python Code)

Max Activating Token Index: 356

Text #6

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5882. Min Act: -0.0001

Data Index: 1615922 (Python Code)

Max Activating Token Index: 961

Text #7

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5527. Min Act: -0.0001

Data Index: 1582649 (Python Code)

Max Activating Token Index: 279

Text #8

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1640036 (Python Code)

Max Activating Token Index: 284

Text #9

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1646625 (Python Code)

Max Activating Token Index: 33

Text #10

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5643. Min Act: -0.0001

Data Index: 1650361 (Python Code)

Max Activating Token Index: 835

Text #11

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5589. Min Act: -0.0001

Data Index: 1532258 (Python Code)

Max Activating Token Index: 337

Text #12

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5091. Min Act: -0.0001

Data Index: 1617005 (Python Code)

Max Activating Token Index: 347

Text #13

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5116. Min Act: -0.0001

Data Index: 1482458 (Python Code)

Max Activating Token Index: 84

Text #14

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5250. Min Act: -0.0001

Data Index: 1372880 (Python Code)

Max Activating Token Index: 580

Text #15

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5095. Min Act: -0.0001

Data Index: 1647878 (Python Code)

Max Activating Token Index: 52

Text #16

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5239. Min Act: -0.0001

Data Index: 1521695 (Python Code)

Max Activating Token Index: 464

Text #17

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5354. Min Act: -0.0001

Data Index: 1610806 (Python Code)

Max Activating Token Index: 632

Text #18

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.4804. Min Act: -0.0001

Data Index: 1545851 (Python Code)

Max Activating Token Index: 47

Text #19

Max Range: 0.6663. Min Range: -0.6663

Max Act: 0.5086. Min Act: -0.0001

Data Index: 1383840 (Python Code)

Max Activating Token Index: 679