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

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

Neuron 4002 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1212. Min Act: -0.0001

Data Index: 950583 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1060867 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1059. Min Act: -0.0001

Data Index: 15062 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1057. Min Act: -0.0002

Data Index: 872351 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1016. Min Act: -0.0001

Data Index: 636218 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1002. Min Act: -0.0001

Data Index: 650882 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1047. Min Act: -0.0001

Data Index: 547956 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0999. Min Act: -0.0001

Data Index: 364295 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1081. Min Act: -0.0001

Data Index: 29912 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1101. Min Act: -0.0001

Data Index: 84471 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0951. Min Act: -0.0001

Data Index: 471878 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0959. Min Act: -0.0001

Data Index: 318988 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1002. Min Act: -0.0001

Data Index: 232990 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1075701 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0958. Min Act: -0.0001

Data Index: 130607 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1119354 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1097697 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0960. Min Act: -0.0001

Data Index: 167541 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0976. Min Act: -0.0001

Data Index: 355626 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0968. Min Act: -0.0001

Data Index: 765074 (C4 (Web Text))

Max Activating Token Index: 18