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

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

Neuron 3541 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.3847. Min Act: -0.0000

Data Index: 21164 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1342668 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.3250. Min Act: -0.0000

Data Index: 819597 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.3151. Min Act: -0.0000

Data Index: 300487 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.3111. Min Act: -0.0000

Data Index: 550714 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1190855 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2848. Min Act: -0.0000

Data Index: 629585 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1239060 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2802. Min Act: -0.0000

Data Index: 736892 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1244851 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2959. Min Act: -0.0000

Data Index: 485206 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2833. Min Act: -0.0000

Data Index: 707457 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2545. Min Act: -0.0000

Data Index: 623550 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1085905 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2611. Min Act: -0.0000

Data Index: 155374 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2512. Min Act: -0.0000

Data Index: 764153 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1003137 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2655. Min Act: -0.0000

Data Index: 504472 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2440. Min Act: -0.0000

Data Index: 584443 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2522. Min Act: -0.0000

Data Index: 482378 (C4 (Web Text))

Max Activating Token Index: 807