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

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

Neuron 3100 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2561. Min Range: -2.2561

Max Act: 2.2561. Min Act: -0.0000

Data Index: 505525 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.4905. Min Act: -0.0000

Data Index: 126519 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.5607. Min Act: -0.0000

Data Index: 460505 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1120068 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.3917. Min Act: -0.0000

Data Index: 1246436 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.2580. Min Act: -0.0000

Data Index: 1263014 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.2090. Min Act: -0.0000

Data Index: 708392 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.0967. Min Act: -0.0000

Data Index: 459012 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.0945. Min Act: -0.0000

Data Index: 98227 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.0478. Min Act: -0.0000

Data Index: 177467 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.0672. Min Act: -0.0000

Data Index: 877996 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.0511. Min Act: -0.0000

Data Index: 24312 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 2.2561. Min Range: -2.2561

Max Act: 0.9777. Min Act: -0.0000

Data Index: 682386 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.0657. Min Act: -0.0000

Data Index: 799412 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 2.2561. Min Range: -2.2561

Max Act: 0.9471. Min Act: -0.0000

Data Index: 587897 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 2.2561. Min Range: -2.2561

Max Act: 0.9541. Min Act: -0.0000

Data Index: 784769 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 2.2561. Min Range: -2.2561

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1118721 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 2.2561. Min Range: -2.2561

Max Act: 0.9739. Min Act: -0.0000

Data Index: 843902 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 2.2561. Min Range: -2.2561

Max Act: 0.9654. Min Act: -0.0000

Data Index: 718109 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 2.2561. Min Range: -2.2561

Max Act: 0.9407. Min Act: -0.0000

Data Index: 669099 (C4 (Web Text))

Max Activating Token Index: 619