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

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

Neuron 3875 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: 0.0824. Min Range: -0.0824

Max Act: 0.0824. Min Act: -0.0002

Data Index: 203695 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1386197 (Python Code)

Max Activating Token Index: 393

Text #2

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0694. Min Act: -0.0002

Data Index: 523540 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1596532 (Python Code)

Max Activating Token Index: 925

Text #4

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0667. Min Act: -0.0002

Data Index: 477621 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0654. Min Act: -0.0002

Data Index: 960860 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0644. Min Act: -0.0002

Data Index: 620317 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0636. Min Act: -0.0002

Data Index: 700417 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0607. Min Act: -0.0002

Data Index: 331101 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0581. Min Act: -0.0002

Data Index: 345810 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0592. Min Act: -0.0002

Data Index: 720728 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0590. Min Act: -0.0002

Data Index: 46551 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1644041 (Python Code)

Max Activating Token Index: 303

Text #13

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0549. Min Act: -0.0002

Data Index: 370943 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0543. Min Act: -0.0002

Data Index: 834305 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0555. Min Act: -0.0002

Data Index: 722531 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0546. Min Act: -0.0002

Data Index: 772148 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0530. Min Act: -0.0002

Data Index: 813130 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0541. Min Act: -0.0002

Data Index: 138099 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.0824. Min Range: -0.0824

Max Act: 0.0518. Min Act: -0.0002

Data Index: 8304 (C4 (Web Text))

Max Activating Token Index: 672