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

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

Neuron 1354 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.9069. Min Act: -0.0000

Data Index: 226864 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.9019. Min Act: -0.0000

Data Index: 785623 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.8379. Min Act: -0.0000

Data Index: 26610 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.8212. Min Act: -0.0000

Data Index: 474862 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.7571. Min Act: -0.0000

Data Index: 162634 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.7991. Min Act: -0.0000

Data Index: 962055 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.7847. Min Act: -0.0000

Data Index: 159710 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.7478. Min Act: -0.0000

Data Index: 885183 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1247454 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.7432. Min Act: -0.0000

Data Index: 80256 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.7380. Min Act: -0.0000

Data Index: 680632 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1321862 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.7926. Min Act: -0.0000

Data Index: 921049 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.6739. Min Act: -0.0000

Data Index: 55748 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.6699. Min Act: -0.0001

Data Index: 672617 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.6745. Min Act: -0.0000

Data Index: 597258 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.6914. Min Act: -0.0000

Data Index: 370207 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.6898. Min Act: -0.0000

Data Index: 426366 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.5997. Min Act: -0.0000

Data Index: 831973 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.9069. Min Range: -0.9069

Max Act: 0.6964. Min Act: -0.0001

Data Index: 130820 (C4 (Web Text))

Max Activating Token Index: 560