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

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

Neuron 2099 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0926. Min Act: -0.0001

Data Index: 761924 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0918. Min Act: -0.0002

Data Index: 520659 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0928. Min Act: -0.0001

Data Index: 274421 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0912. Min Act: -0.0002

Data Index: 715105 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0898. Min Act: -0.0002

Data Index: 161140 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0880. Min Act: -0.0001

Data Index: 342118 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0897. Min Act: -0.0002

Data Index: 962875 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0863. Min Act: -0.0001

Data Index: 106139 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0867. Min Act: -0.0002

Data Index: 615098 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0858. Min Act: -0.0002

Data Index: 868253 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0861. Min Act: -0.0001

Data Index: 494899 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1004870 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0830. Min Act: -0.0001

Data Index: 272182 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0828. Min Act: -0.0001

Data Index: 272097 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1137856 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0853. Min Act: -0.0002

Data Index: 95658 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1316698 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0818. Min Act: -0.0002

Data Index: 329328 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0816. Min Act: -0.0001

Data Index: 653734 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1321504 (C4 (Web Text))

Max Activating Token Index: 375