Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 853 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1073450 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0892. Min Act: -0.0001

Data Index: 303120 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1037521 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1057903 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0862. Min Act: -0.0002

Data Index: 764884 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1135124 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1013395 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0885. Min Act: -0.0002

Data Index: 213855 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0870. Min Act: -0.0002

Data Index: 141968 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0821. Min Act: -0.0002

Data Index: 192456 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1048959 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0881. Min Act: -0.0002

Data Index: 888525 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0871. Min Act: -0.0002

Data Index: 629665 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0865. Min Act: -0.0002

Data Index: 472256 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0854. Min Act: -0.0002

Data Index: 55768 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0830. Min Act: -0.0001

Data Index: 338059 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0866. Min Act: -0.0002

Data Index: 382820 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0845. Min Act: -0.0001

Data Index: 387586 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0843. Min Act: -0.0002

Data Index: 561393 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0829. Min Act: -0.0002

Data Index: 70340 (C4 (Web Text))

Max Activating Token Index: 704