Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2987 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2558. Min Act: -0.0001

Data Index: 576144 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2237. Min Act: -0.0001

Data Index: 1134511 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2133. Min Act: -0.0001

Data Index: 710308 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2062. Min Act: -0.0001

Data Index: 88771 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1905. Min Act: -0.0001

Data Index: 214432 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2144. Min Act: -0.0001

Data Index: 676147 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2002. Min Act: -0.0001

Data Index: 541307 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2282. Min Act: -0.0001

Data Index: 817056 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2053. Min Act: -0.0001

Data Index: 609246 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2124. Min Act: -0.0001

Data Index: 935763 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2137. Min Act: -0.0001

Data Index: 577780 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2131. Min Act: -0.0001

Data Index: 378295 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1186213 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2018. Min Act: -0.0001

Data Index: 1117177 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1964. Min Act: -0.0001

Data Index: 1307073 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2229. Min Act: -0.0001

Data Index: 388934 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1959. Min Act: -0.0001

Data Index: 1007431 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1939. Min Act: -0.0001

Data Index: 634395 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.1823. Min Act: -0.0001

Data Index: 597392 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.2558. Min Range: -0.2558

Max Act: 0.2074. Min Act: -0.0001

Data Index: 207872 (C4 (Web Text))

Max Activating Token Index: 27