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

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

Neuron 3871 in Layer 0

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: 0.0839. Min Range: -0.0839

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1141297 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0787. Min Act: -0.0001

Data Index: 783373 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1351005 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0731. Min Act: -0.0001

Data Index: 111016 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0738. Min Act: -0.0001

Data Index: 681690 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1318176 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1338673 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0706. Min Act: -0.0001

Data Index: 614868 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0704. Min Act: -0.0001

Data Index: 624495 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1247452 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0676. Min Act: -0.0001

Data Index: 205186 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0680. Min Act: -0.0001

Data Index: 612801 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0679. Min Act: -0.0001

Data Index: 111500 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0681. Min Act: -0.0001

Data Index: 321350 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0679. Min Act: -0.0001

Data Index: 677813 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0677. Min Act: -0.0001

Data Index: 614981 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1034853 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0659. Min Act: -0.0001

Data Index: 146195 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0674. Min Act: -0.0001

Data Index: 79299 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0669. Min Act: -0.0001

Data Index: 601259 (C4 (Web Text))

Max Activating Token Index: 921