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

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

Neuron 972 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: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0002

Data Index: 670904 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0845. Min Act: -0.0002

Data Index: 853662 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0837. Min Act: -0.0002

Data Index: 494929 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0829. Min Act: -0.0002

Data Index: 770029 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1211867 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0792. Min Act: -0.0002

Data Index: 522631 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0799. Min Act: -0.0002

Data Index: 301817 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0810. Min Act: -0.0002

Data Index: 35610 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1904 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1304193 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0770. Min Act: -0.0002

Data Index: 3473 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0767. Min Act: -0.0002

Data Index: 570168 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0753. Min Act: -0.0002

Data Index: 368363 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0749. Min Act: -0.0002

Data Index: 284891 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1325675 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0741. Min Act: -0.0002

Data Index: 271214 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0730. Min Act: -0.0002

Data Index: 662263 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1285473 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0722. Min Act: -0.0002

Data Index: 96085 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0742. Min Act: -0.0002

Data Index: 157285 (C4 (Web Text))

Max Activating Token Index: 256