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

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

Neuron 5701 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0868. Min Act: -0.0001

Data Index: 966319 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0754. Min Act: -0.0001

Data Index: 76887 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0721. Min Act: -0.0001

Data Index: 922320 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0802. Min Act: -0.0001

Data Index: 1153689 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0637. Min Act: -0.0001

Data Index: 559815 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1434443 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0718. Min Act: -0.0001

Data Index: 73789 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1149851 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0700. Min Act: -0.0001

Data Index: 939853 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0719. Min Act: -0.0001

Data Index: 396381 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1246264 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0831. Min Act: -0.0001

Data Index: 1624786 (Python Code)

Max Activating Token Index: 33

Text #12

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0767. Min Act: -0.0001

Data Index: 822409 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0525. Min Act: -0.0001

Data Index: 317992 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1450799 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0578. Min Act: -0.0001

Data Index: 433797 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1292113 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0663. Min Act: -0.0001

Data Index: 111884 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0707. Min Act: -0.0001

Data Index: 975011 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0628. Min Act: -0.0001

Data Index: 549171 (C4 (Web Text))

Max Activating Token Index: 411