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

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

Neuron 3037 in Layer 1

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: 0.1946. Min Range: -0.1946

Max Act: 0.1946. Min Act: -0.0002

Data Index: 1534280 (Python Code)

Max Activating Token Index: 108

Text #1

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1889. Min Act: -0.0002

Data Index: 1434655 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1852. Min Act: -0.0002

Data Index: 1490228 (Python Code)

Max Activating Token Index: 129

Text #3

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1853. Min Act: -0.0002

Data Index: 1629241 (Python Code)

Max Activating Token Index: 193

Text #4

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1853. Min Act: -0.0002

Data Index: 1398886 (Python Code)

Max Activating Token Index: 222

Text #5

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1846. Min Act: -0.0002

Data Index: 1626191 (Python Code)

Max Activating Token Index: 414

Text #6

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1839. Min Act: -0.0002

Data Index: 1462375 (Python Code)

Max Activating Token Index: 178

Text #7

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1818. Min Act: -0.0002

Data Index: 1418297 (Python Code)

Max Activating Token Index: 186

Text #8

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1761. Min Act: -0.0002

Data Index: 1439921 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1774. Min Act: -0.0002

Data Index: 1379319 (Python Code)

Max Activating Token Index: 165

Text #10

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1727. Min Act: -0.0002

Data Index: 1424680 (Python Code)

Max Activating Token Index: 378

Text #11

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1726. Min Act: -0.0002

Data Index: 1516434 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1680. Min Act: -0.0002

Data Index: 1548213 (Python Code)

Max Activating Token Index: 282

Text #13

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1686. Min Act: -0.0002

Data Index: 1543258 (Python Code)

Max Activating Token Index: 247

Text #14

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1719. Min Act: -0.0002

Data Index: 1414937 (Python Code)

Max Activating Token Index: 480

Text #15

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1690. Min Act: -0.0002

Data Index: 1464694 (Python Code)

Max Activating Token Index: 254

Text #16

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1699. Min Act: -0.0002

Data Index: 1610398 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1679. Min Act: -0.0002

Data Index: 1431484 (Python Code)

Max Activating Token Index: 380

Text #18

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1699. Min Act: -0.0002

Data Index: 1545028 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1667. Min Act: -0.0002

Data Index: 1469677 (Python Code)

Max Activating Token Index: 329