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

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

Neuron 809 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: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0002

Data Index: 166099 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0589. Min Act: -0.0002

Data Index: 176612 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0590. Min Act: -0.0002

Data Index: 104129 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0544. Min Act: -0.0002

Data Index: 744039 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1021798 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0524. Min Act: -0.0002

Data Index: 780541 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0528. Min Act: -0.0002

Data Index: 623418 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0527. Min Act: -0.0002

Data Index: 308607 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0517. Min Act: -0.0002

Data Index: 803169 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1306332 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0507. Min Act: -0.0002

Data Index: 811788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0513. Min Act: -0.0002

Data Index: 748295 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1119459 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0510. Min Act: -0.0001

Data Index: 753300 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1201430 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1229713 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0500. Min Act: -0.0002

Data Index: 606524 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0498. Min Act: -0.0002

Data Index: 898748 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0484. Min Act: -0.0002

Data Index: 698861 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0495. Min Act: -0.0002

Data Index: 608117 (C4 (Web Text))

Max Activating Token Index: 147