Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2208 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2878. Min Act: -0.0001

Data Index: 310230 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2659. Min Act: -0.0001

Data Index: 1237614 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2822. Min Act: -0.0001

Data Index: 137748 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2902. Min Act: -0.0001

Data Index: 1057926 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2680. Min Act: -0.0001

Data Index: 1272390 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2738. Min Act: -0.0001

Data Index: 1325784 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2678. Min Act: -0.0001

Data Index: 863506 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2676. Min Act: -0.0001

Data Index: 564798 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2678. Min Act: -0.0001

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2657. Min Act: -0.0001

Data Index: 1006308 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2658. Min Act: -0.0001

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2667. Min Act: -0.0001

Data Index: 679558 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2708. Min Act: -0.0001

Data Index: 1108496 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2594. Min Act: -0.0001

Data Index: 1524402 (Python Code)

Max Activating Token Index: 215

Text #14

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2513. Min Act: -0.0001

Data Index: 1037864 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2494. Min Act: -0.0001

Data Index: 211160 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2498. Min Act: -0.0001

Data Index: 617195 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2581. Min Act: -0.0001

Data Index: 1308815 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2480. Min Act: -0.0001

Data Index: 200578 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2469. Min Act: -0.0001

Data Index: 429798 (C4 (Web Text))

Max Activating Token Index: 96