Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2378 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0654. Min Act: -0.0004

Data Index: 1295601 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0515. Min Act: -0.0004

Data Index: 982661 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0456. Min Act: -0.0004

Data Index: 379500 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0457. Min Act: -0.0004

Data Index: 877821 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0478. Min Act: -0.0004

Data Index: 149647 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0473. Min Act: -0.0004

Data Index: 1204362 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0529. Min Act: -0.0004

Data Index: 1024016 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0440. Min Act: -0.0004

Data Index: 663243 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0427. Min Act: -0.0004

Data Index: 1319744 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0435. Min Act: -0.0004

Data Index: 796374 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0414. Min Act: -0.0004

Data Index: 1274295 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0430. Min Act: -0.0004

Data Index: 967981 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0387. Min Act: -0.0004

Data Index: 689073 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0426. Min Act: -0.0004

Data Index: 992606 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0423. Min Act: -0.0004

Data Index: 969077 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0434. Min Act: -0.0004

Data Index: 678412 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0436. Min Act: -0.0004

Data Index: 247584 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0433. Min Act: -0.0004

Data Index: 1317992 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0399. Min Act: -0.0004

Data Index: 787695 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0400. Min Act: -0.0004

Data Index: 479640 (C4 (Web Text))

Max Activating Token Index: 282