Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 120 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1005281 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0677. Min Act: -0.0002

Data Index: 596684 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0646. Min Act: -0.0001

Data Index: 287791 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0630. Min Act: -0.0002

Data Index: 375961 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0642. Min Act: -0.0002

Data Index: 825625 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1050052 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1026445 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0596. Min Act: -0.0002

Data Index: 122908 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0585. Min Act: -0.0002

Data Index: 585135 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0589. Min Act: -0.0002

Data Index: 931644 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0600. Min Act: -0.0002

Data Index: 703888 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0586. Min Act: -0.0002

Data Index: 77869 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1287185 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1351979 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0586. Min Act: -0.0002

Data Index: 971117 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0538. Min Act: -0.0002

Data Index: 326891 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1253866 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0546. Min Act: -0.0002

Data Index: 698705 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0540. Min Act: -0.0002

Data Index: 969618 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.0781. Min Range: -0.0781

Max Act: 0.0568. Min Act: -0.0002

Data Index: 676079 (C4 (Web Text))

Max Activating Token Index: 286