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

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

Neuron 3653 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5788. Min Range: -5.5788

Max Act: 5.5788. Min Act: 0.0000

Data Index: 1353331 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 5.5788. Min Range: -5.5788

Max Act: 5.1664. Min Act: 0.0000

Data Index: 872718 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.8043. Min Act: 0.0000

Data Index: 624954 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.7720. Min Act: 0.0000

Data Index: 1203571 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.8933. Min Act: -0.0000

Data Index: 149602 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.7494. Min Act: 0.0000

Data Index: 315826 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.6827. Min Act: -0.0000

Data Index: 357290 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.6928. Min Act: -0.0000

Data Index: 1039022 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.5207. Min Act: -0.0000

Data Index: 79764 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.6017. Min Act: 0.0000

Data Index: 343082 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.7383. Min Act: -0.0000

Data Index: 849287 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.3635. Min Act: -0.0000

Data Index: 601395 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.3877. Min Act: 0.0000

Data Index: 683861 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.5331. Min Act: -0.0000

Data Index: 1290553 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.5052. Min Act: 0.0000

Data Index: 225479 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.6915. Min Act: -0.0000

Data Index: 197258 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.4414. Min Act: 0.0000

Data Index: 64528 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.4420. Min Act: -0.0000

Data Index: 1153470 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.3862. Min Act: 0.0000

Data Index: 190088 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 5.5788. Min Range: -5.5788

Max Act: 4.5498. Min Act: -0.0000

Data Index: 39578 (C4 (Web Text))

Max Activating Token Index: 641