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

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

Neuron 1655 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: 1.3497. Min Range: -1.3497

Max Act: 1.3497. Min Act: -0.0001

Data Index: 1413954 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1727. Min Act: -0.0001

Data Index: 1600492 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1546. Min Act: -0.0001

Data Index: 1639018 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1548. Min Act: -0.0001

Data Index: 1557039 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1359. Min Act: -0.0001

Data Index: 1603104 (Python Code)

Max Activating Token Index: 96

Text #5

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1217. Min Act: -0.0001

Data Index: 1390497 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1236. Min Act: -0.0001

Data Index: 1577372 (Python Code)

Max Activating Token Index: 38

Text #7

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1343. Min Act: -0.0001

Data Index: 1499350 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1275. Min Act: -0.0001

Data Index: 1628679 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1209. Min Act: -0.0001

Data Index: 1540562 (Python Code)

Max Activating Token Index: 80

Text #10

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.1142. Min Act: -0.0001

Data Index: 1407223 (Python Code)

Max Activating Token Index: 81

Text #11

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0900. Min Act: -0.0001

Data Index: 1511484 (Python Code)

Max Activating Token Index: 53

Text #12

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0957. Min Act: -0.0001

Data Index: 1498074 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0864. Min Act: -0.0001

Data Index: 1513812 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0884. Min Act: -0.0001

Data Index: 1593799 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0693. Min Act: -0.0001

Data Index: 1592375 (Python Code)

Max Activating Token Index: 19

Text #16

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0622. Min Act: -0.0002

Data Index: 1366795 (Python Code)

Max Activating Token Index: 44

Text #17

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0668. Min Act: -0.0001

Data Index: 1588346 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0659. Min Act: -0.0001

Data Index: 1607043 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 1.3497. Min Range: -1.3497

Max Act: 1.0803. Min Act: -0.0001

Data Index: 1378513 (Python Code)

Max Activating Token Index: 18