Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1967 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1040. Min Act: -0.0001

Data Index: 362344 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0994. Min Act: -0.0001

Data Index: 830092 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1326253 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0952. Min Act: -0.0001

Data Index: 473304 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0926. Min Act: -0.0001

Data Index: 63161 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0936. Min Act: -0.0001

Data Index: 772543 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0936. Min Act: -0.0001

Data Index: 32290 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0898. Min Act: -0.0001

Data Index: 143224 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0931. Min Act: -0.0001

Data Index: 900282 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1235068 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0912. Min Act: -0.0001

Data Index: 846889 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0894. Min Act: -0.0001

Data Index: 965536 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0819. Min Act: -0.0001

Data Index: 233209 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1074859 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1290924 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0826. Min Act: -0.0001

Data Index: 825902 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0824. Min Act: -0.0001

Data Index: 213632 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0823. Min Act: -0.0001

Data Index: 337396 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0790. Min Act: -0.0001

Data Index: 374592 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0809. Min Act: -0.0001

Data Index: 68979 (C4 (Web Text))

Max Activating Token Index: 702