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

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

Neuron 3270 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1426. Min Act: -0.0002

Data Index: 1498243 (Python Code)

Max Activating Token Index: 683

Text #1

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1358. Min Act: -0.0002

Data Index: 1570918 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1381. Min Act: -0.0002

Data Index: 1468041 (Python Code)

Max Activating Token Index: 774

Text #3

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1408337 (Python Code)

Max Activating Token Index: 89

Text #4

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1307. Min Act: -0.0002

Data Index: 1579407 (Python Code)

Max Activating Token Index: 822

Text #5

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1349. Min Act: -0.0002

Data Index: 1608548 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1279. Min Act: -0.0002

Data Index: 1386322 (Python Code)

Max Activating Token Index: 994

Text #7

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1267. Min Act: -0.0002

Data Index: 1531079 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1418419 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1273. Min Act: -0.0002

Data Index: 1479432 (Python Code)

Max Activating Token Index: 366

Text #10

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1234. Min Act: -0.0002

Data Index: 1599442 (Python Code)

Max Activating Token Index: 636

Text #11

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1214. Min Act: -0.0002

Data Index: 1620115 (Python Code)

Max Activating Token Index: 349

Text #12

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1207. Min Act: -0.0002

Data Index: 1573110 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1197. Min Act: -0.0002

Data Index: 1374825 (Python Code)

Max Activating Token Index: 111

Text #14

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1190. Min Act: -0.0002

Data Index: 1621336 (Python Code)

Max Activating Token Index: 418

Text #15

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1171. Min Act: -0.0002

Data Index: 1514001 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1653276 (Python Code)

Max Activating Token Index: 422

Text #17

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1148. Min Act: -0.0002

Data Index: 1466516 (Python Code)

Max Activating Token Index: 440

Text #18

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1622599 (Python Code)

Max Activating Token Index: 227

Text #19

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1473445 (Python Code)

Max Activating Token Index: 49