Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3592 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8385. Min Range: -4.8385

Max Act: 4.8385. Min Act: -0.0000

Data Index: 322953 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 4.8385. Min Range: -4.8385

Max Act: 4.7867. Min Act: -0.0000

Data Index: 1306388 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.9738. Min Act: -0.0000

Data Index: 653252 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.7557. Min Act: -0.0000

Data Index: 1281839 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 4.8385. Min Range: -4.8385

Max Act: 4.0010. Min Act: -0.0000

Data Index: 1196415 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.8690. Min Act: -0.0000

Data Index: 875416 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.6860. Min Act: -0.0000

Data Index: 706803 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.6679. Min Act: -0.0000

Data Index: 49714 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.7611. Min Act: -0.0000

Data Index: 55899 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.5991. Min Act: -0.0000

Data Index: 521240 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.8008. Min Act: -0.0000

Data Index: 1197155 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.7205. Min Act: -0.0000

Data Index: 501227 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.4789. Min Act: -0.0000

Data Index: 769947 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.5610. Min Act: -0.0000

Data Index: 82709 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.1860. Min Act: -0.0000

Data Index: 233541 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.5095. Min Act: -0.0000

Data Index: 665252 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.4506. Min Act: 0.0000

Data Index: 843146 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.4187. Min Act: -0.0000

Data Index: 454352 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.4090. Min Act: -0.0000

Data Index: 313146 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 4.8385. Min Range: -4.8385

Max Act: 3.3339. Min Act: -0.0000

Data Index: 163033 (C4 (Web Text))

Max Activating Token Index: 564