Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4100 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.1083. Min Act: -0.0000

Data Index: 760547 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0866. Min Act: -0.0000

Data Index: 1288760 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0905. Min Act: -0.0000

Data Index: 756165 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0863. Min Act: -0.0000

Data Index: 277155 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0791. Min Act: -0.0000

Data Index: 737708 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0804. Min Act: -0.0000

Data Index: 957497 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0773. Min Act: -0.0000

Data Index: 593686 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0736. Min Act: -0.0000

Data Index: 745469 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1218629 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1539419 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1265506 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0760. Min Act: -0.0000

Data Index: 841497 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1350233 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0728. Min Act: -0.0000

Data Index: 1220762 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0748. Min Act: -0.0000

Data Index: 1525503 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0697. Min Act: -0.0000

Data Index: 967443 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0742. Min Act: -0.0000

Data Index: 786947 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0710. Min Act: -0.0000

Data Index: 73877 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1145955 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.1083. Min Range: -0.1083

Max Act: 0.0708. Min Act: -0.0000

Data Index: 490197 (C4 (Web Text))

Max Activating Token Index: 60