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

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

Neuron 2180 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1645. Min Act: -0.0002

Data Index: 1427731 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1649. Min Act: -0.0002

Data Index: 1365921 (Python Code)

Max Activating Token Index: 153

Text #2

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1537. Min Act: -0.0002

Data Index: 1407200 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1344. Min Act: -0.0002

Data Index: 1370289 (Python Code)

Max Activating Token Index: 98

Text #4

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1394. Min Act: -0.0002

Data Index: 1457894 (Python Code)

Max Activating Token Index: 90

Text #5

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1467. Min Act: -0.0002

Data Index: 1544736 (Python Code)

Max Activating Token Index: 925

Text #6

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1241. Min Act: -0.0002

Data Index: 1373548 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1239. Min Act: -0.0002

Data Index: 1566271 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1610181 (Python Code)

Max Activating Token Index: 261

Text #9

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1302. Min Act: -0.0002

Data Index: 1597357 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1307. Min Act: -0.0002

Data Index: 1410027 (Python Code)

Max Activating Token Index: 42

Text #11

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1331. Min Act: -0.0002

Data Index: 1632844 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1239. Min Act: -0.0002

Data Index: 1387299 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1289. Min Act: -0.0002

Data Index: 1638411 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1186. Min Act: -0.0002

Data Index: 1625806 (Python Code)

Max Activating Token Index: 68

Text #15

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1236. Min Act: -0.0002

Data Index: 1360358 (Python Code)

Max Activating Token Index: 613

Text #16

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1234. Min Act: -0.0002

Data Index: 1365142 (Python Code)

Max Activating Token Index: 225

Text #17

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1252. Min Act: -0.0002

Data Index: 1373068 (Python Code)

Max Activating Token Index: 804

Text #18

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1614678 (Python Code)

Max Activating Token Index: 339

Text #19

Max Range: 0.1649. Min Range: -0.1649

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1525819 (Python Code)

Max Activating Token Index: 15