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

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

Neuron 2642 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2653. Min Act: -0.0001

Data Index: 351150 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2732. Min Act: -0.0001

Data Index: 1166246 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2373. Min Act: -0.0001

Data Index: 1330985 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2366. Min Act: -0.0001

Data Index: 1183972 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2226. Min Act: -0.0001

Data Index: 864163 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2260. Min Act: -0.0001

Data Index: 37198 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2216. Min Act: -0.0000

Data Index: 618735 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1130968 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2113. Min Act: -0.0001

Data Index: 133472 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2179. Min Act: -0.0000

Data Index: 702939 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2063. Min Act: -0.0001

Data Index: 575957 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2212. Min Act: -0.0001

Data Index: 384270 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2013. Min Act: -0.0001

Data Index: 626206 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2042. Min Act: -0.0001

Data Index: 589123 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2021. Min Act: -0.0001

Data Index: 655112 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2001. Min Act: -0.0001

Data Index: 732786 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1991. Min Act: -0.0001

Data Index: 301935 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1905. Min Act: -0.0000

Data Index: 205159 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2086. Min Act: -0.0001

Data Index: 1191463 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1933. Min Act: -0.0001

Data Index: 386418 (C4 (Web Text))

Max Activating Token Index: 834