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

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

Neuron 1835 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5086. Min Range: -5.5086

Max Act: 5.5086. Min Act: -0.0001

Data Index: 543488 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 5.5086. Min Range: -5.5086

Max Act: 5.0032. Min Act: -0.0001

Data Index: 143005 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 5.5086. Min Range: -5.5086

Max Act: 5.1153. Min Act: -0.0001

Data Index: 135088 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 5.5086. Min Range: -5.5086

Max Act: 5.1068. Min Act: -0.0001

Data Index: 901439 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 5.5086. Min Range: -5.5086

Max Act: 5.2905. Min Act: -0.0001

Data Index: 894280 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 5.5086. Min Range: -5.5086

Max Act: 5.0714. Min Act: -0.0001

Data Index: 1298303 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.8859. Min Act: -0.0001

Data Index: 1112751 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 5.5086. Min Range: -5.5086

Max Act: 5.1974. Min Act: -0.0001

Data Index: 1110339 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 5.5086. Min Range: -5.5086

Max Act: 5.1489. Min Act: -0.0001

Data Index: 842987 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.9044. Min Act: -0.0001

Data Index: 748477 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.9039. Min Act: -0.0001

Data Index: 1012079 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.8936. Min Act: -0.0001

Data Index: 217545 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.7932. Min Act: -0.0001

Data Index: 187081 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.8329. Min Act: -0.0001

Data Index: 1091384 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.9775. Min Act: -0.0001

Data Index: 216539 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.9616. Min Act: -0.0001

Data Index: 533061 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.9065. Min Act: -0.0001

Data Index: 106972 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.8738. Min Act: -0.0001

Data Index: 390182 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.7509. Min Act: -0.0001

Data Index: 920938 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 5.5086. Min Range: -5.5086

Max Act: 4.7095. Min Act: -0.0001

Data Index: 780443 (C4 (Web Text))

Max Activating Token Index: 20