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

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

Neuron 2934 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.1029. Min Act: -0.0004

Data Index: 250162 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0979. Min Act: -0.0004

Data Index: 775227 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0923. Min Act: -0.0004

Data Index: 525698 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0960. Min Act: -0.0004

Data Index: 739246 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0950. Min Act: -0.0004

Data Index: 327493 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0890. Min Act: -0.0004

Data Index: 484739 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0851. Min Act: -0.0004

Data Index: 1159563 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0842. Min Act: -0.0004

Data Index: 203803 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0878. Min Act: -0.0004

Data Index: 370752 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0839. Min Act: -0.0004

Data Index: 1210800 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0868. Min Act: -0.0004

Data Index: 686395 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0858. Min Act: -0.0004

Data Index: 84605 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0860. Min Act: -0.0004

Data Index: 1187336 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0844. Min Act: -0.0004

Data Index: 1005883 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0849. Min Act: -0.0004

Data Index: 72572 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0873. Min Act: -0.0004

Data Index: 406245 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0809. Min Act: -0.0004

Data Index: 1175680 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0838. Min Act: -0.0004

Data Index: 1057702 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0843. Min Act: -0.0004

Data Index: 1287485 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.1029. Min Range: -0.1029

Max Act: 0.0830. Min Act: -0.0004

Data Index: 136874 (C4 (Web Text))

Max Activating Token Index: 50