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

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

Neuron 2816 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.7455. Min Act: 0.0000

Data Index: 1516933 (Python Code)

Max Activating Token Index: 538

Text #1

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.3334. Min Act: 0.0000

Data Index: 1513425 (Python Code)

Max Activating Token Index: 515

Text #2

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.1279. Min Act: 0.0000

Data Index: 1626273 (Python Code)

Max Activating Token Index: 922

Text #3

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.1934. Min Act: 0.0000

Data Index: 1423650 (Python Code)

Max Activating Token Index: 202

Text #4

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.0794. Min Act: 0.0000

Data Index: 1578573 (Python Code)

Max Activating Token Index: 340

Text #5

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.1801. Min Act: 0.0000

Data Index: 1531373 (Python Code)

Max Activating Token Index: 853

Text #6

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.1058. Min Act: 0.0000

Data Index: 1443097 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.8484. Min Act: 0.0000

Data Index: 1412001 (Python Code)

Max Activating Token Index: 192

Text #8

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.0622. Min Act: 0.0000

Data Index: 1628904 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.9206. Min Act: 0.0000

Data Index: 1520141 (Python Code)

Max Activating Token Index: 474

Text #10

Max Range: 2.7455. Min Range: -2.7455

Max Act: 2.0274. Min Act: 0.0000

Data Index: 1503802 (Python Code)

Max Activating Token Index: 618

Text #11

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.9965. Min Act: 0.0000

Data Index: 1645641 (Python Code)

Max Activating Token Index: 531

Text #12

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.9710. Min Act: 0.0000

Data Index: 1550566 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.9786. Min Act: 0.0000

Data Index: 1423479 (Python Code)

Max Activating Token Index: 49

Text #14

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.9926. Min Act: 0.0000

Data Index: 1380913 (Python Code)

Max Activating Token Index: 221

Text #15

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.9540. Min Act: 0.0000

Data Index: 1644122 (Python Code)

Max Activating Token Index: 436

Text #16

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.8303. Min Act: 0.0000

Data Index: 1459369 (Python Code)

Max Activating Token Index: 280

Text #17

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.8301. Min Act: 0.0000

Data Index: 1480487 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.9214. Min Act: 0.0000

Data Index: 1580533 (Python Code)

Max Activating Token Index: 355

Text #19

Max Range: 2.7455. Min Range: -2.7455

Max Act: 1.8804. Min Act: 0.0000

Data Index: 1505893 (Python Code)

Max Activating Token Index: 989