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

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

Neuron 1273 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1283. Min Act: -0.0003

Data Index: 884517 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1148. Min Act: -0.0003

Data Index: 702352 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1235. Min Act: -0.0003

Data Index: 1090631 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1081. Min Act: -0.0003

Data Index: 42714 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1025. Min Act: -0.0003

Data Index: 548211 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0968. Min Act: -0.0003

Data Index: 1192745 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0971. Min Act: -0.0003

Data Index: 546231 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1161. Min Act: -0.0003

Data Index: 847987 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1061. Min Act: -0.0003

Data Index: 590360 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0951. Min Act: -0.0003

Data Index: 1283081 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1019. Min Act: -0.0003

Data Index: 84588 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0911. Min Act: -0.0003

Data Index: 672596 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0951. Min Act: -0.0003

Data Index: 884188 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0951. Min Act: -0.0003

Data Index: 1209407 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0951. Min Act: -0.0003

Data Index: 126155 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.1021. Min Act: -0.0003

Data Index: 87937 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0944. Min Act: -0.0003

Data Index: 1224835 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0908. Min Act: -0.0003

Data Index: 774805 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0967. Min Act: -0.0003

Data Index: 471303 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.1283. Min Range: -0.1283

Max Act: 0.0897. Min Act: -0.0003

Data Index: 788405 (C4 (Web Text))

Max Activating Token Index: 537