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

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

Neuron 2136 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1513426 (Python Code)

Max Activating Token Index: 270

Text #1

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3032. Min Act: -0.0001

Data Index: 1647653 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2804. Min Act: -0.0000

Data Index: 1634385 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1623737 (Python Code)

Max Activating Token Index: 119

Text #4

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1609345 (Python Code)

Max Activating Token Index: 319

Text #5

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2305. Min Act: -0.0001

Data Index: 1639762 (Python Code)

Max Activating Token Index: 345

Text #6

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2324. Min Act: -0.0001

Data Index: 1619749 (Python Code)

Max Activating Token Index: 611

Text #7

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2222. Min Act: -0.0001

Data Index: 1580550 (Python Code)

Max Activating Token Index: 615

Text #8

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2095. Min Act: -0.0001

Data Index: 1486241 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2149. Min Act: -0.0001

Data Index: 1452322 (Python Code)

Max Activating Token Index: 436

Text #10

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2220. Min Act: -0.0001

Data Index: 1412362 (Python Code)

Max Activating Token Index: 758

Text #11

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2196. Min Act: -0.0001

Data Index: 1636711 (Python Code)

Max Activating Token Index: 461

Text #12

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1498361 (Python Code)

Max Activating Token Index: 342

Text #13

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2172. Min Act: -0.0001

Data Index: 1629492 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1647903 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1580088 (Python Code)

Max Activating Token Index: 141

Text #16

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1365091 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2101. Min Act: -0.0001

Data Index: 1568158 (Python Code)

Max Activating Token Index: 848

Text #18

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2186. Min Act: -0.0001

Data Index: 1551860 (Python Code)

Max Activating Token Index: 736

Text #19

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1385026 (Python Code)

Max Activating Token Index: 319