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

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

Neuron 3978 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: 0.1069. Min Range: -0.1069

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1316975 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0001

Data Index: 575696 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0969. Min Act: -0.0001

Data Index: 456731 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0897. Min Act: -0.0002

Data Index: 883358 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0963. Min Act: -0.0002

Data Index: 751153 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0929. Min Act: -0.0002

Data Index: 349835 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1159063 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0855. Min Act: -0.0001

Data Index: 182004 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0787. Min Act: -0.0001

Data Index: 490027 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0818. Min Act: -0.0001

Data Index: 599666 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0865. Min Act: -0.0002

Data Index: 790213 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0939. Min Act: -0.0002

Data Index: 478600 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0886. Min Act: -0.0001

Data Index: 957786 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0827. Min Act: -0.0002

Data Index: 297057 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0800. Min Act: -0.0001

Data Index: 818870 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0764. Min Act: -0.0001

Data Index: 199006 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0820. Min Act: -0.0002

Data Index: 816078 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0857. Min Act: -0.0001

Data Index: 610993 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0777. Min Act: -0.0002

Data Index: 524672 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0733. Min Act: -0.0001

Data Index: 586132 (C4 (Web Text))

Max Activating Token Index: 561