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

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

Neuron 109 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: 0.0667. Min Range: -0.0667

Max Act: 0.0667. Min Act: -0.0002

Data Index: 758861 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0563. Min Act: -0.0002

Data Index: 169700 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0606. Min Act: -0.0002

Data Index: 693085 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1011858 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0565. Min Act: -0.0002

Data Index: 643246 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0517. Min Act: -0.0002

Data Index: 482721 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1164568 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0516. Min Act: -0.0002

Data Index: 158359 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0502. Min Act: -0.0002

Data Index: 632800 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0496. Min Act: -0.0002

Data Index: 821436 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0517. Min Act: -0.0002

Data Index: 315817 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0497. Min Act: -0.0002

Data Index: 649975 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1019445 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0490. Min Act: -0.0002

Data Index: 100423 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0489. Min Act: -0.0002

Data Index: 819047 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0484. Min Act: -0.0002

Data Index: 610492 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0464. Min Act: -0.0002

Data Index: 705386 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1147614 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0473. Min Act: -0.0002

Data Index: 821601 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0465. Min Act: -0.0002

Data Index: 950482 (C4 (Web Text))

Max Activating Token Index: 373