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

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

Neuron 3866 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: 0.1491. Min Range: -0.1491

Max Act: 0.1491. Min Act: -0.0002

Data Index: 1498347 (Python Code)

Max Activating Token Index: 59

Text #1

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1428. Min Act: -0.0002

Data Index: 709849 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1313. Min Act: -0.0002

Data Index: 898368 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1296. Min Act: -0.0002

Data Index: 1435877 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1364. Min Act: -0.0002

Data Index: 1595158 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1328. Min Act: -0.0002

Data Index: 1562446 (Python Code)

Max Activating Token Index: 235

Text #6

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1269. Min Act: -0.0002

Data Index: 1507521 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1478073 (Python Code)

Max Activating Token Index: 241

Text #8

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1296. Min Act: -0.0002

Data Index: 1629942 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1470198 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1308. Min Act: -0.0002

Data Index: 79453 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1490041 (Python Code)

Max Activating Token Index: 169

Text #12

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1415321 (Python Code)

Max Activating Token Index: 489

Text #13

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1627945 (Python Code)

Max Activating Token Index: 798

Text #14

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1400. Min Act: -0.0002

Data Index: 1634869 (Python Code)

Max Activating Token Index: 274

Text #15

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1236. Min Act: -0.0002

Data Index: 1636472 (Python Code)

Max Activating Token Index: 679

Text #16

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1209. Min Act: -0.0002

Data Index: 1641856 (Python Code)

Max Activating Token Index: 875

Text #17

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1307. Min Act: -0.0002

Data Index: 1389562 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1160. Min Act: -0.0002

Data Index: 1561149 (Python Code)

Max Activating Token Index: 525

Text #19

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1193. Min Act: -0.0002

Data Index: 1472290 (Python Code)

Max Activating Token Index: 16