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

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

Neuron 1084 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1322500 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0503. Min Act: -0.0001

Data Index: 30794 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0479. Min Act: -0.0002

Data Index: 919027 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0486. Min Act: -0.0002

Data Index: 560358 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0481. Min Act: -0.0001

Data Index: 591521 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0478. Min Act: -0.0002

Data Index: 560370 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0456. Min Act: -0.0001

Data Index: 869041 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0456. Min Act: -0.0001

Data Index: 701089 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0463. Min Act: -0.0001

Data Index: 935572 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1344053 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0447. Min Act: -0.0001

Data Index: 168641 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0446. Min Act: -0.0001

Data Index: 449124 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0436. Min Act: -0.0002

Data Index: 70858 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0436. Min Act: -0.0001

Data Index: 21803 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1347869 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1111371 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0425. Min Act: -0.0001

Data Index: 681002 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1096396 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0422. Min Act: -0.0002

Data Index: 278169 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1141728 (C4 (Web Text))

Max Activating Token Index: 499