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

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

Neuron 1698 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1036. Min Act: -0.0000

Data Index: 868160 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1031. Min Act: -0.0000

Data Index: 439302 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1001505 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0000

Data Index: 497580 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1197259 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0931. Min Act: -0.0000

Data Index: 826479 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0942. Min Act: -0.0000

Data Index: 606391 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0952. Min Act: -0.0000

Data Index: 325093 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0925. Min Act: -0.0000

Data Index: 270436 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0845. Min Act: -0.0000

Data Index: 889537 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0878. Min Act: -0.0000

Data Index: 864319 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0933. Min Act: -0.0000

Data Index: 264935 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0835. Min Act: -0.0000

Data Index: 664401 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0864. Min Act: -0.0000

Data Index: 458001 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0891. Min Act: -0.0000

Data Index: 773683 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1557659 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0863. Min Act: -0.0000

Data Index: 586677 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0839. Min Act: -0.0000

Data Index: 288672 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0837. Min Act: -0.0000

Data Index: 1138625 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1506514 (Python Code)

Max Activating Token Index: 166