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

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

Neuron 1731 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: 0.2918. Min Range: -0.2918

Max Act: 0.2918. Min Act: -0.0000

Data Index: 848477 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2469. Min Act: -0.0000

Data Index: 115341 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2363. Min Act: -0.0000

Data Index: 542908 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2108. Min Act: -0.0000

Data Index: 671111 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2159. Min Act: -0.0000

Data Index: 254379 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1084920 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1259371 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2038. Min Act: -0.0000

Data Index: 169514 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.2053. Min Act: -0.0000

Data Index: 706303 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1970. Min Act: -0.0000

Data Index: 102973 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1964. Min Act: -0.0000

Data Index: 468272 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1934. Min Act: -0.0000

Data Index: 340474 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1878. Min Act: -0.0000

Data Index: 183536 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1888. Min Act: -0.0000

Data Index: 844976 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1821. Min Act: -0.0000

Data Index: 315315 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1289978 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1853. Min Act: -0.0000

Data Index: 916202 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1041562 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1212790 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.2918. Min Range: -0.2918

Max Act: 0.1787. Min Act: -0.0000

Data Index: 792880 (C4 (Web Text))

Max Activating Token Index: 980