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

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

Neuron 5491 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1624077 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1385. Min Act: -0.0001

Data Index: 1584363 (Python Code)

Max Activating Token Index: 21

Text #2

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1508757 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1447228 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1529891 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1361. Min Act: -0.0001

Data Index: 1633062 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1459654 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1380664 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1637426 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1356. Min Act: -0.0001

Data Index: 1394302 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1397330 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1469707 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1543215 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1342. Min Act: -0.0001

Data Index: 1607242 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1530594 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1525129 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1535521 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1434719 (Python Code)

Max Activating Token Index: 31

Text #18

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1532214 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1632480 (Python Code)

Max Activating Token Index: 42