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

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

Neuron 357 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: 0.0836. Min Range: -0.0836

Max Act: 0.0836. Min Act: -0.0001

Data Index: 716569 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0750. Min Act: -0.0001

Data Index: 294663 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0701. Min Act: -0.0002

Data Index: 673969 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0668. Min Act: -0.0001

Data Index: 806340 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1235066 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0647. Min Act: -0.0002

Data Index: 798735 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0647. Min Act: -0.0001

Data Index: 418152 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0616. Min Act: -0.0001

Data Index: 503724 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1071165 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0632. Min Act: -0.0001

Data Index: 844609 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0605. Min Act: -0.0002

Data Index: 164307 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1006933 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0571. Min Act: -0.0002

Data Index: 762849 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1558641 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0590. Min Act: -0.0002

Data Index: 635577 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0554. Min Act: -0.0002

Data Index: 284655 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0596. Min Act: -0.0001

Data Index: 338859 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1358367 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0546. Min Act: -0.0001

Data Index: 908502 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0575. Min Act: -0.0001

Data Index: 975052 (C4 (Web Text))

Max Activating Token Index: 87