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

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

Neuron 1567 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1964. Min Act: -0.0001

Data Index: 1383891 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1438. Min Act: -0.0001

Data Index: 1383182 (Python Code)

Max Activating Token Index: 391

Text #2

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1671. Min Act: -0.0001

Data Index: 1576209 (Python Code)

Max Activating Token Index: 321

Text #3

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1435. Min Act: -0.0001

Data Index: 1404621 (Python Code)

Max Activating Token Index: 461

Text #4

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1639014 (Python Code)

Max Activating Token Index: 184

Text #5

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1389134 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1636919 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1440570 (Python Code)

Max Activating Token Index: 153

Text #8

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1405604 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1536794 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1390294 (Python Code)

Max Activating Token Index: 884

Text #11

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1557180 (Python Code)

Max Activating Token Index: 513

Text #12

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1563866 (Python Code)

Max Activating Token Index: 713

Text #13

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1583399 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1512925 (Python Code)

Max Activating Token Index: 170

Text #15

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1636055 (Python Code)

Max Activating Token Index: 73

Text #16

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1502424 (Python Code)

Max Activating Token Index: 280

Text #17

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1375668 (Python Code)

Max Activating Token Index: 197

Text #18

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1641608 (Python Code)

Max Activating Token Index: 614

Text #19

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1435607 (Python Code)

Max Activating Token Index: 220