Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 809 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1509. Min Act: -0.0002

Data Index: 376447 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1145. Min Act: -0.0001

Data Index: 1115606 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1068. Min Act: -0.0001

Data Index: 261093 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1087. Min Act: -0.0001

Data Index: 940417 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1016. Min Act: -0.0001

Data Index: 554861 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1045. Min Act: -0.0002

Data Index: 239497 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1076599 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0956. Min Act: -0.0001

Data Index: 391175 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1523691 (Python Code)

Max Activating Token Index: 244

Text #9

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0976. Min Act: -0.0002

Data Index: 874403 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1282939 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0951. Min Act: -0.0002

Data Index: 100681 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1234133 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1239741 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0960. Min Act: -0.0002

Data Index: 550905 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0950. Min Act: -0.0002

Data Index: 927516 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0905. Min Act: -0.0002

Data Index: 161035 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0974. Min Act: -0.0002

Data Index: 1197090 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0875. Min Act: -0.0002

Data Index: 185539 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0928. Min Act: -0.0002

Data Index: 503753 (C4 (Web Text))

Max Activating Token Index: 620