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

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

Neuron 4432 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.9483. Min Act: -0.0000

Data Index: 128108 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.9737. Min Act: -0.0000

Data Index: 140724 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.8251. Min Act: -0.0000

Data Index: 133783 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.8414. Min Act: -0.0000

Data Index: 338779 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1103729 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.8145. Min Act: -0.0000

Data Index: 827556 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7295. Min Act: -0.0000

Data Index: 354069 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7476. Min Act: -0.0000

Data Index: 667459 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7698. Min Act: -0.0000

Data Index: 729483 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7850. Min Act: -0.0000

Data Index: 809226 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1102136 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7317. Min Act: -0.0000

Data Index: 282077 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7350. Min Act: -0.0000

Data Index: 1139500 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7550. Min Act: -0.0000

Data Index: 260038 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7238. Min Act: -0.0000

Data Index: 442861 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7577. Min Act: -0.0000

Data Index: 311769 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7538. Min Act: -0.0000

Data Index: 587182 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7376. Min Act: -0.0000

Data Index: 42549 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7334. Min Act: -0.0000

Data Index: 817906 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.9737. Min Range: -0.9737

Max Act: 0.7334. Min Act: -0.0000

Data Index: 803651 (C4 (Web Text))

Max Activating Token Index: 492