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

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

Neuron 2613 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1435744 (Python Code)

Max Activating Token Index: 402

Text #1

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1443318 (Python Code)

Max Activating Token Index: 662

Text #2

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1393. Min Act: -0.0002

Data Index: 1398503 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1456317 (Python Code)

Max Activating Token Index: 813

Text #4

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1575155 (Python Code)

Max Activating Token Index: 749

Text #5

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1301. Min Act: -0.0001

Data Index: 1414783 (Python Code)

Max Activating Token Index: 58

Text #6

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1396867 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1297. Min Act: -0.0002

Data Index: 1366205 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1623609 (Python Code)

Max Activating Token Index: 680

Text #9

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1555320 (Python Code)

Max Activating Token Index: 362

Text #10

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1413201 (Python Code)

Max Activating Token Index: 89

Text #11

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1517880 (Python Code)

Max Activating Token Index: 974

Text #12

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1507968 (Python Code)

Max Activating Token Index: 971

Text #13

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1476538 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1264. Min Act: -0.0001

Data Index: 1477482 (Python Code)

Max Activating Token Index: 725

Text #15

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1417939 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1615309 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1407254 (Python Code)

Max Activating Token Index: 165

Text #18

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1513712 (Python Code)

Max Activating Token Index: 630

Text #19

Max Range: 0.1469. Min Range: -0.1469

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1642624 (Python Code)

Max Activating Token Index: 518