Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 135 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1363. Min Act: -0.0002

Data Index: 672106 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1208. Min Act: -0.0002

Data Index: 828503 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1190. Min Act: -0.0002

Data Index: 1315933 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1140. Min Act: -0.0002

Data Index: 529705 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1100. Min Act: -0.0002

Data Index: 833493 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1211321 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1131. Min Act: -0.0002

Data Index: 453545 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1173167 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1080. Min Act: -0.0002

Data Index: 439029 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1075. Min Act: -0.0002

Data Index: 563467 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1085. Min Act: -0.0002

Data Index: 513422 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1081. Min Act: -0.0002

Data Index: 36876 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1074. Min Act: -0.0002

Data Index: 712404 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1044. Min Act: -0.0002

Data Index: 25832 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1022. Min Act: -0.0002

Data Index: 757952 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1017. Min Act: -0.0002

Data Index: 1197997 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1021. Min Act: -0.0002

Data Index: 29354 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1043777 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1024. Min Act: -0.0002

Data Index: 713870 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1145349 (C4 (Web Text))

Max Activating Token Index: 184