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

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

Neuron 1778 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0564. Min Act: -0.0003

Data Index: 210382 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0581. Min Act: -0.0003

Data Index: 462599 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0575. Min Act: -0.0003

Data Index: 540260 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0581. Min Act: -0.0003

Data Index: 345393 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0557. Min Act: -0.0003

Data Index: 927108 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0581. Min Act: -0.0003

Data Index: 263781 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1326359 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0544. Min Act: -0.0003

Data Index: 852600 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0542. Min Act: -0.0003

Data Index: 513558 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0536. Min Act: -0.0003

Data Index: 454775 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0541. Min Act: -0.0003

Data Index: 529364 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0496. Min Act: -0.0003

Data Index: 811674 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0486. Min Act: -0.0003

Data Index: 642313 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1155132 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0488. Min Act: -0.0003

Data Index: 170435 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0465. Min Act: -0.0003

Data Index: 441238 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0473. Min Act: -0.0003

Data Index: 721737 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1081106 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0478. Min Act: -0.0003

Data Index: 131558 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0465. Min Act: -0.0003

Data Index: 735231 (C4 (Web Text))

Max Activating Token Index: 830