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

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

Neuron 521 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: 1.3665. Min Range: -1.3665

Max Act: 1.3665. Min Act: -0.0002

Data Index: 1509505 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2426. Min Act: -0.0002

Data Index: 1567610 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2211. Min Act: -0.0002

Data Index: 1618612 (Python Code)

Max Activating Token Index: 785

Text #3

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2756. Min Act: -0.0002

Data Index: 1488974 (Python Code)

Max Activating Token Index: 955

Text #4

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2734. Min Act: -0.0002

Data Index: 1446509 (Python Code)

Max Activating Token Index: 122

Text #5

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2721. Min Act: -0.0002

Data Index: 1615269 (Python Code)

Max Activating Token Index: 680

Text #6

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2066. Min Act: -0.0002

Data Index: 1474609 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2081. Min Act: -0.0002

Data Index: 1436655 (Python Code)

Max Activating Token Index: 364

Text #8

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1890. Min Act: -0.0002

Data Index: 1469405 (Python Code)

Max Activating Token Index: 857

Text #9

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2158. Min Act: -0.0002

Data Index: 1491272 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2258. Min Act: -0.0002

Data Index: 1450913 (Python Code)

Max Activating Token Index: 699

Text #11

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2011. Min Act: -0.0002

Data Index: 1411366 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2178. Min Act: -0.0002

Data Index: 1454384 (Python Code)

Max Activating Token Index: 912

Text #13

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2368. Min Act: -0.0002

Data Index: 1585789 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.2129. Min Act: -0.0002

Data Index: 1376797 (Python Code)

Max Activating Token Index: 265

Text #15

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1875. Min Act: -0.0002

Data Index: 1362364 (Python Code)

Max Activating Token Index: 196

Text #16

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1533. Min Act: -0.0002

Data Index: 1472703 (Python Code)

Max Activating Token Index: 558

Text #17

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1685. Min Act: -0.0002

Data Index: 1544820 (Python Code)

Max Activating Token Index: 714

Text #18

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1767. Min Act: -0.0002

Data Index: 1452628 (Python Code)

Max Activating Token Index: 780

Text #19

Max Range: 1.3665. Min Range: -1.3665

Max Act: 1.1607. Min Act: -0.0002

Data Index: 1544957 (Python Code)

Max Activating Token Index: 992