Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1140 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5403. Min Act: -0.0002

Data Index: 2692 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5087. Min Act: -0.0002

Data Index: 358794 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4849. Min Act: -0.0002

Data Index: 346975 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4914. Min Act: -0.0002

Data Index: 1342191 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4703. Min Act: -0.0002

Data Index: 249597 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4403. Min Act: -0.0002

Data Index: 794958 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4716. Min Act: -0.0002

Data Index: 1296596 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4654. Min Act: -0.0002

Data Index: 753421 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4569. Min Act: -0.0002

Data Index: 1070249 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4365. Min Act: -0.0002

Data Index: 1305377 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4528. Min Act: -0.0002

Data Index: 879627 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4653. Min Act: -0.0002

Data Index: 1121073 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4688. Min Act: -0.0002

Data Index: 162847 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4196. Min Act: -0.0002

Data Index: 778806 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4562. Min Act: -0.0002

Data Index: 1254087 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4206. Min Act: -0.0002

Data Index: 393380 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4280. Min Act: -0.0002

Data Index: 390269 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3993. Min Act: -0.0002

Data Index: 1085213 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4099. Min Act: -0.0002

Data Index: 1279677 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4102. Min Act: -0.0002

Data Index: 766703 (C4 (Web Text))

Max Activating Token Index: 952