Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2081 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1304. Min Act: -0.0001

Data Index: 836881 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1295. Min Act: -0.0001

Data Index: 894132 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1283. Min Act: -0.0001

Data Index: 440256 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1262. Min Act: -0.0001

Data Index: 776169 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1163421 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1102. Min Act: -0.0001

Data Index: 160400 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1176. Min Act: -0.0001

Data Index: 712360 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1039. Min Act: -0.0001

Data Index: 371594 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1004685 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1083. Min Act: -0.0001

Data Index: 763496 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1076. Min Act: -0.0001

Data Index: 625426 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1065. Min Act: -0.0001

Data Index: 49440 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1098866 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1026. Min Act: -0.0001

Data Index: 48006 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1059. Min Act: -0.0001

Data Index: 43022 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1023. Min Act: -0.0001

Data Index: 503813 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1059. Min Act: -0.0001

Data Index: 800750 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1220831 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1114913 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.1304. Min Range: -0.1304

Max Act: 0.1044. Min Act: -0.0001

Data Index: 464366 (C4 (Web Text))

Max Activating Token Index: 310