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

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

Neuron 6004 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: 2.4281. Min Range: -2.4281

Max Act: 2.4256. Min Act: -0.0002

Data Index: 1570626 (Python Code)

Max Activating Token Index: 697

Text #1

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.4281. Min Act: -0.0002

Data Index: 1512397 (Python Code)

Max Activating Token Index: 892

Text #2

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3775. Min Act: -0.0002

Data Index: 1645358 (Python Code)

Max Activating Token Index: 802

Text #3

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3400. Min Act: -0.0002

Data Index: 1384404 (Python Code)

Max Activating Token Index: 675

Text #4

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3679. Min Act: -0.0002

Data Index: 1366899 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3608. Min Act: -0.0002

Data Index: 1528700 (Python Code)

Max Activating Token Index: 674

Text #6

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3306. Min Act: -0.0002

Data Index: 1654926 (Python Code)

Max Activating Token Index: 789

Text #7

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3998. Min Act: -0.0002

Data Index: 1641914 (Python Code)

Max Activating Token Index: 763

Text #8

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3634. Min Act: -0.0002

Data Index: 1403237 (Python Code)

Max Activating Token Index: 854

Text #9

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3450. Min Act: -0.0002

Data Index: 1475935 (Python Code)

Max Activating Token Index: 634

Text #10

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3047. Min Act: -0.0002

Data Index: 1575658 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3503. Min Act: -0.0002

Data Index: 1405254 (Python Code)

Max Activating Token Index: 939

Text #12

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3039. Min Act: -0.0002

Data Index: 1640764 (Python Code)

Max Activating Token Index: 751

Text #13

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.2970. Min Act: -0.0002

Data Index: 1598316 (Python Code)

Max Activating Token Index: 794

Text #14

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.3037. Min Act: -0.0002

Data Index: 1468361 (Python Code)

Max Activating Token Index: 808

Text #15

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.2523. Min Act: -0.0002

Data Index: 1427569 (Python Code)

Max Activating Token Index: 732

Text #16

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.2565. Min Act: -0.0002

Data Index: 1655427 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.2579. Min Act: -0.0002

Data Index: 1452212 (Python Code)

Max Activating Token Index: 515

Text #18

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.2835. Min Act: -0.0002

Data Index: 1527059 (Python Code)

Max Activating Token Index: 786

Text #19

Max Range: 2.4281. Min Range: -2.4281

Max Act: 2.2028. Min Act: -0.0002

Data Index: 1593791 (Python Code)

Max Activating Token Index: 936