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

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

Neuron 4741 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: 1.4396. Min Range: -1.4396

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1476329 (Python Code)

Max Activating Token Index: 160

Text #1

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.4396. Min Act: -0.0000

Data Index: 1608080 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1590332 (Python Code)

Max Activating Token Index: 335

Text #3

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1561205 (Python Code)

Max Activating Token Index: 179

Text #4

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1485800 (Python Code)

Max Activating Token Index: 167

Text #5

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1854. Min Act: -0.0001

Data Index: 1610211 (Python Code)

Max Activating Token Index: 910

Text #6

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1406955 (Python Code)

Max Activating Token Index: 833

Text #7

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.2422. Min Act: -0.0001

Data Index: 1540201 (Python Code)

Max Activating Token Index: 897

Text #8

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1603. Min Act: -0.0000

Data Index: 1373136 (Python Code)

Max Activating Token Index: 908

Text #9

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1350. Min Act: -0.0000

Data Index: 1625469 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1442623 (Python Code)

Max Activating Token Index: 984

Text #11

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1583. Min Act: -0.0001

Data Index: 1401281 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1155. Min Act: -0.0001

Data Index: 1642957 (Python Code)

Max Activating Token Index: 403

Text #13

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1448822 (Python Code)

Max Activating Token Index: 891

Text #14

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.0599. Min Act: -0.0000

Data Index: 1563890 (Python Code)

Max Activating Token Index: 186

Text #15

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1193. Min Act: -0.0000

Data Index: 1584059 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1486764 (Python Code)

Max Activating Token Index: 203

Text #17

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1370710 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 1.4396. Min Range: -1.4396

Max Act: 1.1310. Min Act: -0.0001

Data Index: 1622432 (Python Code)

Max Activating Token Index: 778

Text #19

Max Range: 1.4396. Min Range: -1.4396

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1408204 (Python Code)

Max Activating Token Index: 239