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

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

Neuron 4476 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: 0.2836. Min Range: -0.2836

Max Act: 0.2701. Min Act: -0.0000

Data Index: 655814 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1192167 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1539745 (Python Code)

Max Activating Token Index: 938

Text #3

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1577774 (Python Code)

Max Activating Token Index: 646

Text #4

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2535. Min Act: -0.0000

Data Index: 88425 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1586286 (Python Code)

Max Activating Token Index: 594

Text #6

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1598978 (Python Code)

Max Activating Token Index: 835

Text #7

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2482. Min Act: -0.0000

Data Index: 589763 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1459503 (Python Code)

Max Activating Token Index: 888

Text #9

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1491514 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2269. Min Act: -0.0000

Data Index: 1511161 (Python Code)

Max Activating Token Index: 565

Text #11

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2164. Min Act: -0.0000

Data Index: 791607 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1379377 (Python Code)

Max Activating Token Index: 592

Text #13

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2063. Min Act: -0.0000

Data Index: 872178 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1384285 (Python Code)

Max Activating Token Index: 465

Text #15

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1479568 (Python Code)

Max Activating Token Index: 893

Text #16

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1579312 (Python Code)

Max Activating Token Index: 622

Text #17

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2080. Min Act: -0.0000

Data Index: 814350 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1260988 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.2836. Min Range: -0.2836

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1570822 (Python Code)

Max Activating Token Index: 936