Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2986 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1999. Min Act: -0.0001

Data Index: 678538 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.2017. Min Act: -0.0001

Data Index: 427550 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1234061 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1926. Min Act: -0.0001

Data Index: 1232202 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.2036. Min Act: -0.0001

Data Index: 937068 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.2003. Min Act: -0.0001

Data Index: 356079 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1073279 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1975. Min Act: -0.0001

Data Index: 432571 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1907. Min Act: -0.0001

Data Index: 789462 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1977. Min Act: -0.0001

Data Index: 545340 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1888. Min Act: -0.0001

Data Index: 1137690 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.2068. Min Act: -0.0001

Data Index: 868842 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1869. Min Act: -0.0001

Data Index: 859269 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1911. Min Act: -0.0001

Data Index: 483584 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1947. Min Act: -0.0001

Data Index: 1284092 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1894. Min Act: -0.0001

Data Index: 375323 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1726. Min Act: -0.0001

Data Index: 1061652 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1846. Min Act: -0.0001

Data Index: 623249 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1751. Min Act: -0.0001

Data Index: 350580 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.2068. Min Range: -0.2068

Max Act: 0.1803. Min Act: -0.0001

Data Index: 641669 (C4 (Web Text))

Max Activating Token Index: 76