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

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

Neuron 3533 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1677. Min Act: -0.0000

Data Index: 402492 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1541. Min Act: -0.0000

Data Index: 270916 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1507. Min Act: -0.0000

Data Index: 648501 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1113169 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1355. Min Act: -0.0000

Data Index: 406724 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1311. Min Act: -0.0000

Data Index: 877476 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1310352 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1400. Min Act: -0.0000

Data Index: 331505 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1364. Min Act: -0.0000

Data Index: 675971 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1147414 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1419552 (Python Code)

Max Activating Token Index: 758

Text #11

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1177278 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1369. Min Act: -0.0000

Data Index: 121728 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1330. Min Act: -0.0000

Data Index: 887520 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1035941 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1204. Min Act: -0.0000

Data Index: 898048 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1413. Min Act: -0.0000

Data Index: 1415007 (Python Code)

Max Activating Token Index: 262

Text #17

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1287. Min Act: -0.0000

Data Index: 35153 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1149798 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1268. Min Act: -0.0000

Data Index: 654081 (C4 (Web Text))

Max Activating Token Index: 903