Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2620 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2487. Min Act: -0.0001

Data Index: 1502393 (Python Code)

Max Activating Token Index: 656

Text #1

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1468845 (Python Code)

Max Activating Token Index: 614

Text #2

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2103. Min Act: -0.0001

Data Index: 1467572 (Python Code)

Max Activating Token Index: 193

Text #3

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1606674 (Python Code)

Max Activating Token Index: 903

Text #4

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2128. Min Act: -0.0001

Data Index: 1427097 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1991. Min Act: -0.0001

Data Index: 1423215 (Python Code)

Max Activating Token Index: 756

Text #6

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1957. Min Act: -0.0001

Data Index: 1529716 (Python Code)

Max Activating Token Index: 869

Text #7

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1950. Min Act: -0.0001

Data Index: 1384813 (Python Code)

Max Activating Token Index: 900

Text #8

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.2074. Min Act: -0.0001

Data Index: 1634798 (Python Code)

Max Activating Token Index: 599

Text #9

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1904. Min Act: -0.0001

Data Index: 1519348 (Python Code)

Max Activating Token Index: 779

Text #10

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1544780 (Python Code)

Max Activating Token Index: 496

Text #11

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1933. Min Act: -0.0001

Data Index: 1599843 (Python Code)

Max Activating Token Index: 396

Text #12

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1854. Min Act: -0.0001

Data Index: 1448077 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1796. Min Act: -0.0001

Data Index: 1410007 (Python Code)

Max Activating Token Index: 837

Text #14

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1836. Min Act: -0.0001

Data Index: 1589582 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1762. Min Act: -0.0001

Data Index: 1446871 (Python Code)

Max Activating Token Index: 695

Text #16

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1484293 (Python Code)

Max Activating Token Index: 782

Text #17

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1460822 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1467620 (Python Code)

Max Activating Token Index: 523

Text #19

Max Range: 0.2487. Min Range: -0.2487

Max Act: 0.1773. Min Act: -0.0001

Data Index: 1497192 (Python Code)

Max Activating Token Index: 336