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

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

Neuron 782 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1076. Min Act: -0.0000

Data Index: 339798 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1076. Min Act: -0.0000

Data Index: 31205 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1014. Min Act: -0.0000

Data Index: 437506 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0960. Min Act: -0.0000

Data Index: 441164 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0918. Min Act: -0.0000

Data Index: 1173901 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0957. Min Act: -0.0000

Data Index: 926005 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0954. Min Act: -0.0000

Data Index: 857844 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0959. Min Act: -0.0000

Data Index: 70268 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0955. Min Act: -0.0000

Data Index: 223592 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0916. Min Act: -0.0000

Data Index: 856972 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0966. Min Act: -0.0000

Data Index: 76635 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0915. Min Act: -0.0000

Data Index: 917521 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0884. Min Act: -0.0000

Data Index: 697587 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0947. Min Act: -0.0000

Data Index: 423404 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0914. Min Act: -0.0000

Data Index: 814709 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0882. Min Act: -0.0000

Data Index: 677694 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0906. Min Act: -0.0000

Data Index: 358287 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1283068 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1526505 (Python Code)

Max Activating Token Index: 540

Text #19

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0870. Min Act: -0.0000

Data Index: 330615 (C4 (Web Text))

Max Activating Token Index: 713