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

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

Neuron 1756 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1573510 (Python Code)

Max Activating Token Index: 612

Text #1

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.8038. Min Act: -0.0000

Data Index: 541772 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1422765 (Python Code)

Max Activating Token Index: 137

Text #3

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1533790 (Python Code)

Max Activating Token Index: 99

Text #4

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1564238 (Python Code)

Max Activating Token Index: 680

Text #5

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1224404 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1511719 (Python Code)

Max Activating Token Index: 749

Text #7

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6513. Min Act: -0.0000

Data Index: 157395 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.6055. Min Act: -0.0000

Data Index: 377226 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1474277 (Python Code)

Max Activating Token Index: 918

Text #10

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1649780 (Python Code)

Max Activating Token Index: 519

Text #11

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5602. Min Act: -0.0001

Data Index: 1624052 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5862. Min Act: -0.0000

Data Index: 286179 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1442987 (Python Code)

Max Activating Token Index: 521

Text #14

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1358410 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5311. Min Act: -0.0000

Data Index: 728549 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1410760 (Python Code)

Max Activating Token Index: 592

Text #17

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1449373 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.5316. Min Act: -0.0000

Data Index: 400304 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.8265. Min Range: -0.8265

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1353357 (C4 (Web Text))

Max Activating Token Index: 309