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

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

Neuron 468 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.5209. Min Act: -0.0001

Data Index: 1073313 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.4697. Min Act: -0.0001

Data Index: 359449 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.5501. Min Act: -0.0001

Data Index: 1083658 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.4380. Min Act: -0.0000

Data Index: 1402922 (Python Code)

Max Activating Token Index: 682

Text #4

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.4134. Min Act: -0.0000

Data Index: 430043 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.4131. Min Act: -0.0001

Data Index: 1217794 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.3301. Min Act: -0.0001

Data Index: 237210 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.4232. Min Act: -0.0001

Data Index: 180025 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.2756. Min Act: -0.0001

Data Index: 1608726 (Python Code)

Max Activating Token Index: 283

Text #9

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.2074. Min Act: -0.0000

Data Index: 1364901 (Python Code)

Max Activating Token Index: 238

Text #10

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.2667. Min Act: -0.0001

Data Index: 741241 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.2508. Min Act: -0.0001

Data Index: 1578970 (Python Code)

Max Activating Token Index: 478

Text #12

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.2053. Min Act: -0.0001

Data Index: 922752 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.2174. Min Act: -0.0001

Data Index: 1458509 (Python Code)

Max Activating Token Index: 547

Text #14

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.2143. Min Act: -0.0001

Data Index: 545005 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.1333. Min Act: -0.0001

Data Index: 1607463 (Python Code)

Max Activating Token Index: 325

Text #16

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.1663. Min Act: -0.0001

Data Index: 1376503 (Python Code)

Max Activating Token Index: 212

Text #17

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1550213 (Python Code)

Max Activating Token Index: 207

Text #18

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.2137. Min Act: -0.0001

Data Index: 1527728 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 1.5501. Min Range: -1.5501

Max Act: 1.1025. Min Act: -0.0000

Data Index: 1524368 (Python Code)

Max Activating Token Index: 341