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

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

Neuron 555 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: 0.4354. Min Range: -0.4354

Max Act: 0.4354. Min Act: -0.0001

Data Index: 1529891 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.4354. Min Act: -0.0001

Data Index: 1633062 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.4187. Min Act: -0.0001

Data Index: 1649218 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.4204. Min Act: -0.0001

Data Index: 1445840 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.4023. Min Act: -0.0001

Data Index: 1557861 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3916. Min Act: -0.0001

Data Index: 1449404 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3968. Min Act: -0.0001

Data Index: 1520071 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3968. Min Act: -0.0001

Data Index: 1497786 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3862. Min Act: -0.0001

Data Index: 1444513 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3800. Min Act: -0.0001

Data Index: 1387721 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3823. Min Act: -0.0001

Data Index: 1398600 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1437742 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1520192 (Python Code)

Max Activating Token Index: 11

Text #13

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1639261 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3803. Min Act: -0.0001

Data Index: 1374784 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3731. Min Act: -0.0001

Data Index: 1399512 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3731. Min Act: -0.0001

Data Index: 1521663 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3731. Min Act: -0.0001

Data Index: 1386910 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3731. Min Act: -0.0001

Data Index: 1572390 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3829. Min Act: -0.0001

Data Index: 1621248 (Python Code)

Max Activating Token Index: 63