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

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

Neuron 924 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: 0.0857. Min Range: -0.0857

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1405092 (Python Code)

Max Activating Token Index: 147

Text #1

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1363732 (Python Code)

Max Activating Token Index: 723

Text #2

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1579185 (Python Code)

Max Activating Token Index: 226

Text #3

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1481443 (Python Code)

Max Activating Token Index: 825

Text #4

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1594440 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1376120 (Python Code)

Max Activating Token Index: 114

Text #6

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1401937 (Python Code)

Max Activating Token Index: 418

Text #7

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1443913 (Python Code)

Max Activating Token Index: 542

Text #8

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1578330 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1519141 (Python Code)

Max Activating Token Index: 430

Text #10

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1542432 (Python Code)

Max Activating Token Index: 966

Text #11

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1465597 (Python Code)

Max Activating Token Index: 910

Text #12

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1524112 (Python Code)

Max Activating Token Index: 550

Text #13

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1605415 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1487234 (Python Code)

Max Activating Token Index: 680

Text #15

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1609225 (Python Code)

Max Activating Token Index: 501

Text #16

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1515230 (Python Code)

Max Activating Token Index: 113

Text #17

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1480599 (Python Code)

Max Activating Token Index: 364

Text #18

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1398679 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1583868 (Python Code)

Max Activating Token Index: 220