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

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

Neuron 1099 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: 1.3311. Min Range: -1.3311

Max Act: 1.3099. Min Act: -0.0002

Data Index: 1380682 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.3099. Min Act: -0.0002

Data Index: 1370125 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.2978. Min Act: -0.0002

Data Index: 1575841 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.3311. Min Act: -0.0002

Data Index: 1628626 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.2176. Min Act: -0.0002

Data Index: 1384030 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.2141. Min Act: -0.0002

Data Index: 1526264 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1844. Min Act: -0.0002

Data Index: 1605059 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.2105. Min Act: -0.0002

Data Index: 1600045 (Python Code)

Max Activating Token Index: 75

Text #8

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1879. Min Act: -0.0002

Data Index: 1519736 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1941. Min Act: -0.0002

Data Index: 1535829 (Python Code)

Max Activating Token Index: 646

Text #10

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1611. Min Act: -0.0002

Data Index: 1396097 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1936. Min Act: -0.0002

Data Index: 1401678 (Python Code)

Max Activating Token Index: 53

Text #12

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1427. Min Act: -0.0002

Data Index: 1550799 (Python Code)

Max Activating Token Index: 260

Text #13

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1643. Min Act: -0.0002

Data Index: 1371790 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1657. Min Act: -0.0002

Data Index: 1410424 (Python Code)

Max Activating Token Index: 889

Text #15

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1634. Min Act: -0.0002

Data Index: 1482687 (Python Code)

Max Activating Token Index: 48

Text #16

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1473. Min Act: -0.0002

Data Index: 1396098 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1690. Min Act: -0.0002

Data Index: 1393597 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1495. Min Act: -0.0002

Data Index: 1628643 (Python Code)

Max Activating Token Index: 812

Text #19

Max Range: 1.3311. Min Range: -1.3311

Max Act: 1.1738. Min Act: -0.0002

Data Index: 1552528 (Python Code)

Max Activating Token Index: 12