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

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

Neuron 3530 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: 0.6655. Min Range: -0.6655

Max Act: 0.6522. Min Act: -0.0001

Data Index: 1370336 (Python Code)

Max Activating Token Index: 812

Text #1

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6525. Min Act: -0.0001

Data Index: 1397870 (Python Code)

Max Activating Token Index: 697

Text #2

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6641. Min Act: -0.0001

Data Index: 1653334 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6356. Min Act: -0.0001

Data Index: 1399957 (Python Code)

Max Activating Token Index: 54

Text #4

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1556243 (Python Code)

Max Activating Token Index: 38

Text #5

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6655. Min Act: -0.0001

Data Index: 1493827 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6454. Min Act: -0.0001

Data Index: 1554397 (Python Code)

Max Activating Token Index: 987

Text #7

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6459. Min Act: -0.0001

Data Index: 1419843 (Python Code)

Max Activating Token Index: 64

Text #8

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6420. Min Act: -0.0001

Data Index: 1489750 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6344. Min Act: -0.0001

Data Index: 1636920 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6325. Min Act: -0.0001

Data Index: 1592304 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6409. Min Act: -0.0001

Data Index: 1456331 (Python Code)

Max Activating Token Index: 52

Text #12

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6354. Min Act: -0.0001

Data Index: 1520333 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6260. Min Act: -0.0001

Data Index: 1463084 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6307. Min Act: -0.0001

Data Index: 1609200 (Python Code)

Max Activating Token Index: 199

Text #15

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6207. Min Act: -0.0001

Data Index: 1408492 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6119. Min Act: -0.0001

Data Index: 1542605 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6156. Min Act: -0.0001

Data Index: 1653273 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6194. Min Act: -0.0001

Data Index: 1523628 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 0.6655. Min Range: -0.6655

Max Act: 0.6094. Min Act: -0.0001

Data Index: 1448030 (Python Code)

Max Activating Token Index: 172