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

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

Neuron 2659 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1558. Min Act: -0.0003

Data Index: 1532229 (Python Code)

Max Activating Token Index: 219

Text #1

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1464. Min Act: -0.0003

Data Index: 1506639 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1416. Min Act: -0.0003

Data Index: 1444805 (Python Code)

Max Activating Token Index: 843

Text #3

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1486. Min Act: -0.0003

Data Index: 1466528 (Python Code)

Max Activating Token Index: 260

Text #4

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1500. Min Act: -0.0003

Data Index: 1539810 (Python Code)

Max Activating Token Index: 1013

Text #5

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1419. Min Act: -0.0003

Data Index: 1390818 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1347. Min Act: -0.0003

Data Index: 1480882 (Python Code)

Max Activating Token Index: 224

Text #7

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1339. Min Act: -0.0003

Data Index: 1443670 (Python Code)

Max Activating Token Index: 281

Text #8

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1379. Min Act: -0.0003

Data Index: 1441714 (Python Code)

Max Activating Token Index: 747

Text #9

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1348. Min Act: -0.0003

Data Index: 1600566 (Python Code)

Max Activating Token Index: 862

Text #10

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1402. Min Act: -0.0003

Data Index: 1593885 (Python Code)

Max Activating Token Index: 391

Text #11

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1343. Min Act: -0.0003

Data Index: 1519658 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1351. Min Act: -0.0003

Data Index: 1550156 (Python Code)

Max Activating Token Index: 972

Text #13

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1363. Min Act: -0.0003

Data Index: 1448352 (Python Code)

Max Activating Token Index: 274

Text #14

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1393. Min Act: -0.0003

Data Index: 1477847 (Python Code)

Max Activating Token Index: 993

Text #15

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1248. Min Act: -0.0003

Data Index: 1618669 (Python Code)

Max Activating Token Index: 817

Text #16

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1342. Min Act: -0.0003

Data Index: 1393653 (Python Code)

Max Activating Token Index: 993

Text #17

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1325. Min Act: -0.0003

Data Index: 1550764 (Python Code)

Max Activating Token Index: 963

Text #18

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1416. Min Act: -0.0003

Data Index: 1441999 (Python Code)

Max Activating Token Index: 927

Text #19

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1277. Min Act: -0.0003

Data Index: 1545487 (Python Code)

Max Activating Token Index: 743