Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 409 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2571. Min Act: -0.0003

Data Index: 922565 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2410. Min Act: -0.0003

Data Index: 1146022 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2255. Min Act: -0.0003

Data Index: 756853 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2249. Min Act: -0.0003

Data Index: 1304786 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2190. Min Act: -0.0003

Data Index: 226830 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2071. Min Act: -0.0003

Data Index: 332763 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2193. Min Act: -0.0003

Data Index: 450916 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1930. Min Act: -0.0003

Data Index: 303930 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2100. Min Act: -0.0003

Data Index: 161031 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2090. Min Act: -0.0003

Data Index: 261144 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2006. Min Act: -0.0003

Data Index: 988711 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1939. Min Act: -0.0003

Data Index: 1323512 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2010. Min Act: -0.0003

Data Index: 967953 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1911. Min Act: -0.0003

Data Index: 46415 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1946. Min Act: -0.0003

Data Index: 1317875 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1961. Min Act: -0.0003

Data Index: 410863 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2203. Min Act: -0.0003

Data Index: 1068381 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.2014. Min Act: -0.0003

Data Index: 382658 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1911. Min Act: -0.0003

Data Index: 1184082 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.2571. Min Range: -0.2571

Max Act: 0.1859. Min Act: -0.0003

Data Index: 652179 (C4 (Web Text))

Max Activating Token Index: 1004