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

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

Neuron 3799 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.4562. Min Act: -0.0000

Data Index: 476732 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3986. Min Act: -0.0000

Data Index: 395168 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3737. Min Act: -0.0000

Data Index: 427371 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3547. Min Act: -0.0000

Data Index: 687884 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3780. Min Act: -0.0000

Data Index: 896421 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3518. Min Act: -0.0000

Data Index: 799894 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3416. Min Act: -0.0000

Data Index: 566333 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3309. Min Act: -0.0000

Data Index: 871586 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3517. Min Act: -0.0000

Data Index: 936828 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3281. Min Act: -0.0000

Data Index: 979582 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1341111 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3242. Min Act: -0.0000

Data Index: 752297 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3419. Min Act: -0.0000

Data Index: 535705 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3262. Min Act: -0.0000

Data Index: 605105 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3239. Min Act: -0.0000

Data Index: 758541 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3009. Min Act: -0.0000

Data Index: 50437 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3122. Min Act: -0.0000

Data Index: 964389 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1294417 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1279169 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.4562. Min Range: -0.4562

Max Act: 0.3075. Min Act: -0.0000

Data Index: 94485 (C4 (Web Text))

Max Activating Token Index: 198