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

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

Neuron 2743 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: 0.0900. Min Range: -0.0900

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1516847 (Python Code)

Max Activating Token Index: 697

Text #1

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1379637 (Python Code)

Max Activating Token Index: 497

Text #2

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1448822 (Python Code)

Max Activating Token Index: 987

Text #3

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1522018 (Python Code)

Max Activating Token Index: 276

Text #4

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1561932 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1492454 (Python Code)

Max Activating Token Index: 280

Text #6

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1606739 (Python Code)

Max Activating Token Index: 694

Text #7

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0802. Min Act: -0.0002

Data Index: 295799 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1599380 (Python Code)

Max Activating Token Index: 736

Text #9

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1526765 (Python Code)

Max Activating Token Index: 667

Text #10

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1383930 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1623994 (Python Code)

Max Activating Token Index: 614

Text #12

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1508346 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1368130 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1479876 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1376630 (Python Code)

Max Activating Token Index: 221

Text #16

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1553573 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1386559 (Python Code)

Max Activating Token Index: 466

Text #18

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1426368 (Python Code)

Max Activating Token Index: 546

Text #19

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1634772 (Python Code)

Max Activating Token Index: 196