Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 419 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1079126 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2017. Min Act: -0.0001

Data Index: 177173 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1107187 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2216. Min Act: -0.0001

Data Index: 1254150 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1985. Min Act: -0.0001

Data Index: 143785 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2201. Min Act: -0.0001

Data Index: 1143980 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2070. Min Act: -0.0001

Data Index: 574768 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2146. Min Act: -0.0001

Data Index: 1140769 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2134. Min Act: -0.0001

Data Index: 1157713 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2065. Min Act: -0.0001

Data Index: 881848 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2057. Min Act: -0.0001

Data Index: 174258 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2099. Min Act: -0.0001

Data Index: 479644 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2116. Min Act: -0.0001

Data Index: 740247 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1926. Min Act: -0.0001

Data Index: 1006670 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2088. Min Act: -0.0001

Data Index: 949177 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1960. Min Act: -0.0001

Data Index: 938845 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1888. Min Act: -0.0001

Data Index: 1004793 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1961. Min Act: -0.0001

Data Index: 351169 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.1947. Min Act: -0.0001

Data Index: 890672 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.2216. Min Range: -0.2216

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1234388 (C4 (Web Text))

Max Activating Token Index: 814