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

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

Neuron 2199 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2647. Min Act: -0.0002

Data Index: 508300 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2288. Min Act: -0.0002

Data Index: 441822 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2251. Min Act: -0.0002

Data Index: 845601 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2196. Min Act: -0.0002

Data Index: 667993 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2313. Min Act: -0.0002

Data Index: 832624 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1936. Min Act: -0.0002

Data Index: 1146168 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1852. Min Act: -0.0002

Data Index: 833257 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1706. Min Act: -0.0002

Data Index: 1330365 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1973. Min Act: -0.0002

Data Index: 39893 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1767. Min Act: -0.0002

Data Index: 467252 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1955. Min Act: -0.0002

Data Index: 1202235 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1922. Min Act: -0.0002

Data Index: 1077425 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1909. Min Act: -0.0002

Data Index: 1118774 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1960. Min Act: -0.0002

Data Index: 193575 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1812. Min Act: -0.0002

Data Index: 979240 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1867. Min Act: -0.0002

Data Index: 1186196 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1926. Min Act: -0.0002

Data Index: 523458 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1914. Min Act: -0.0002

Data Index: 894180 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.1834. Min Act: -0.0002

Data Index: 3600 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.2647. Min Range: -0.2647

Max Act: 0.2009. Min Act: -0.0002

Data Index: 932377 (C4 (Web Text))

Max Activating Token Index: 804