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

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

Neuron 3046 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1070. Min Act: -0.0000

Data Index: 35807 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0859. Min Act: -0.0001

Data Index: 957388 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1072097 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0801. Min Act: -0.0001

Data Index: 744019 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0796. Min Act: -0.0001

Data Index: 588052 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0796. Min Act: -0.0001

Data Index: 528093 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0763. Min Act: -0.0000

Data Index: 777288 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0815. Min Act: -0.0000

Data Index: 532520 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1096170 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0750. Min Act: -0.0001

Data Index: 898497 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0750. Min Act: -0.0000

Data Index: 100414 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1337993 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0796. Min Act: -0.0000

Data Index: 665212 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0768. Min Act: -0.0000

Data Index: 467239 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0765. Min Act: -0.0000

Data Index: 387208 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1007018 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0744. Min Act: -0.0000

Data Index: 587975 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0733. Min Act: -0.0000

Data Index: 588365 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0731. Min Act: -0.0001

Data Index: 399777 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1177613 (C4 (Web Text))

Max Activating Token Index: 84