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

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

Neuron 648 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: 0.4910. Min Range: -0.4910

Max Act: 0.4852. Min Act: -0.0000

Data Index: 222975 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4910. Min Act: -0.0000

Data Index: 961699 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1174998 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4044. Min Act: -0.0000

Data Index: 422654 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3836. Min Act: -0.0000

Data Index: 270205 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3190. Min Act: -0.0000

Data Index: 699319 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.2936. Min Act: -0.0000

Data Index: 241945 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3795. Min Act: -0.0000

Data Index: 650525 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1020573 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3335. Min Act: -0.0000

Data Index: 721570 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1307389 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.2879. Min Act: -0.0000

Data Index: 889089 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3005. Min Act: -0.0000

Data Index: 999862 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3483. Min Act: -0.0000

Data Index: 1123868 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.2868. Min Act: -0.0000

Data Index: 169260 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.2757. Min Act: -0.0000

Data Index: 896577 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3013. Min Act: -0.0000

Data Index: 781732 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.2597. Min Act: -0.0000

Data Index: 401682 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1346586 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1140768 (C4 (Web Text))

Max Activating Token Index: 144