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

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

Neuron 1686 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: 0.0746. Min Range: -0.0746

Max Act: 0.0746. Min Act: -0.0002

Data Index: 264419 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1644890 (Python Code)

Max Activating Token Index: 825

Text #2

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0648. Min Act: -0.0002

Data Index: 890703 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0636. Min Act: -0.0002

Data Index: 146562 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0636. Min Act: -0.0002

Data Index: 892088 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0635. Min Act: -0.0002

Data Index: 163502 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1366964 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0612. Min Act: -0.0002

Data Index: 523676 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0624. Min Act: -0.0002

Data Index: 148066 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0622. Min Act: -0.0002

Data Index: 793357 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0608. Min Act: -0.0002

Data Index: 681635 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1307720 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1637238 (Python Code)

Max Activating Token Index: 652

Text #13

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0608. Min Act: -0.0002

Data Index: 178075 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0593. Min Act: -0.0002

Data Index: 160913 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0611. Min Act: -0.0002

Data Index: 185536 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1113399 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0590. Min Act: -0.0002

Data Index: 79151 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0606. Min Act: -0.0002

Data Index: 568903 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0597. Min Act: -0.0002

Data Index: 175958 (C4 (Web Text))

Max Activating Token Index: 913