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

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

Neuron 975 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0005

Data Index: 869536 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0539. Min Act: -0.0005

Data Index: 814889 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0516. Min Act: -0.0005

Data Index: 377080 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0525. Min Act: -0.0005

Data Index: 675783 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0538. Min Act: -0.0005

Data Index: 588453 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0530. Min Act: -0.0005

Data Index: 507226 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0529. Min Act: -0.0005

Data Index: 1073767 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0507. Min Act: -0.0005

Data Index: 44557 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0528. Min Act: -0.0005

Data Index: 364046 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0499. Min Act: -0.0005

Data Index: 492838 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0506. Min Act: -0.0005

Data Index: 877319 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0500. Min Act: -0.0005

Data Index: 499542 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0498. Min Act: -0.0005

Data Index: 58223 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0547. Min Act: -0.0005

Data Index: 1276585 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0520. Min Act: -0.0005

Data Index: 112716 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0507. Min Act: -0.0005

Data Index: 380147 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0507. Min Act: -0.0005

Data Index: 463440 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0497. Min Act: -0.0005

Data Index: 58656 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0517. Min Act: -0.0005

Data Index: 319937 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0505. Min Act: -0.0005

Data Index: 276321 (C4 (Web Text))

Max Activating Token Index: 892