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

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

Neuron 2782 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.4674. Min Act: -0.0000

Data Index: 1575827 (Python Code)

Max Activating Token Index: 253

Text #1

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.6429. Min Act: -0.0000

Data Index: 1423978 (Python Code)

Max Activating Token Index: 335

Text #2

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.4549. Min Act: -0.0000

Data Index: 1632468 (Python Code)

Max Activating Token Index: 531

Text #3

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.4091. Min Act: -0.0000

Data Index: 1497571 (Python Code)

Max Activating Token Index: 974

Text #4

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1460562 (Python Code)

Max Activating Token Index: 501

Text #5

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.4033. Min Act: -0.0000

Data Index: 1369071 (Python Code)

Max Activating Token Index: 424

Text #6

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2702. Min Act: -0.0000

Data Index: 1475271 (Python Code)

Max Activating Token Index: 1010

Text #7

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3866. Min Act: -0.0000

Data Index: 1419815 (Python Code)

Max Activating Token Index: 334

Text #8

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3316. Min Act: -0.0000

Data Index: 1548473 (Python Code)

Max Activating Token Index: 503

Text #9

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2812. Min Act: -0.0000

Data Index: 1412359 (Python Code)

Max Activating Token Index: 806

Text #10

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1634628 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2977. Min Act: -0.0000

Data Index: 1416658 (Python Code)

Max Activating Token Index: 952

Text #12

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3689. Min Act: -0.0000

Data Index: 1417879 (Python Code)

Max Activating Token Index: 154

Text #13

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2730. Min Act: -0.0000

Data Index: 1567273 (Python Code)

Max Activating Token Index: 350

Text #14

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2266. Min Act: -0.0000

Data Index: 1424597 (Python Code)

Max Activating Token Index: 902

Text #15

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2008. Min Act: -0.0000

Data Index: 1570990 (Python Code)

Max Activating Token Index: 861

Text #16

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1551775 (Python Code)

Max Activating Token Index: 450

Text #17

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1922. Min Act: -0.0000

Data Index: 1448947 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1429533 (Python Code)

Max Activating Token Index: 953

Text #19

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.1486. Min Act: -0.0000

Data Index: 1386252 (Python Code)

Max Activating Token Index: 616