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

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

Neuron 4343 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.6984. Min Act: -0.0001

Data Index: 153204 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.5058. Min Act: -0.0001

Data Index: 591866 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.8079. Min Act: -0.0001

Data Index: 47851 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.5222. Min Act: -0.0001

Data Index: 817464 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.5226. Min Act: -0.0001

Data Index: 752544 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.3604. Min Act: -0.0001

Data Index: 275902 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.3201. Min Act: -0.0001

Data Index: 411397 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.3998. Min Act: -0.0001

Data Index: 1220715 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.3838. Min Act: -0.0001

Data Index: 1065748 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.3985. Min Act: -0.0001

Data Index: 964824 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.5106. Min Act: -0.0001

Data Index: 694801 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.3745. Min Act: -0.0001

Data Index: 1139035 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.2365. Min Act: -0.0001

Data Index: 676537 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.5182. Min Act: -0.0001

Data Index: 840065 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.3686. Min Act: -0.0001

Data Index: 1178290 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.3260. Min Act: -0.0001

Data Index: 319376 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.3287. Min Act: -0.0001

Data Index: 1257755 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.4599. Min Act: -0.0001

Data Index: 204677 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.0365. Min Act: -0.0001

Data Index: 153396 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 3.8079. Min Range: -3.8079

Max Act: 3.2660. Min Act: -0.0001

Data Index: 347259 (C4 (Web Text))

Max Activating Token Index: 193