Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2778 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1582852 (Python Code)

Max Activating Token Index: 224

Text #1

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1655287 (Python Code)

Max Activating Token Index: 30

Text #2

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1380076 (Python Code)

Max Activating Token Index: 115

Text #3

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1394. Min Act: -0.0001

Data Index: 1429708 (Python Code)

Max Activating Token Index: 38

Text #4

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1574106 (Python Code)

Max Activating Token Index: 529

Text #5

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1568172 (Python Code)

Max Activating Token Index: 550

Text #6

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1397. Min Act: -0.0001

Data Index: 1635837 (Python Code)

Max Activating Token Index: 357

Text #7

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1502824 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1376937 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1375363 (Python Code)

Max Activating Token Index: 324

Text #10

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1406925 (Python Code)

Max Activating Token Index: 389

Text #11

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1511283 (Python Code)

Max Activating Token Index: 517

Text #12

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1609725 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1430462 (Python Code)

Max Activating Token Index: 636

Text #14

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1648474 (Python Code)

Max Activating Token Index: 193

Text #15

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1608800 (Python Code)

Max Activating Token Index: 1000

Text #16

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1469560 (Python Code)

Max Activating Token Index: 456

Text #17

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1545621 (Python Code)

Max Activating Token Index: 324

Text #18

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1510708 (Python Code)

Max Activating Token Index: 956

Text #19

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1474540 (Python Code)

Max Activating Token Index: 459