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

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

Neuron 1921 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1225929 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0863. Min Act: -0.0000

Data Index: 570486 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0842. Min Act: -0.0000

Data Index: 859727 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1311572 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0858. Min Act: -0.0000

Data Index: 517925 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0819. Min Act: -0.0000

Data Index: 640104 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0786. Min Act: -0.0000

Data Index: 177277 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0800. Min Act: -0.0000

Data Index: 715545 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0827. Min Act: -0.0000

Data Index: 402395 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0793. Min Act: -0.0000

Data Index: 775750 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0814. Min Act: -0.0000

Data Index: 273505 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1287919 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0744. Min Act: -0.0000

Data Index: 42998 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0763. Min Act: -0.0000

Data Index: 298338 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1239754 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1026510 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0761. Min Act: -0.0000

Data Index: 917288 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0699. Min Act: -0.0000

Data Index: 1244210 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0784. Min Act: -0.0000

Data Index: 672424 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.1128. Min Range: -0.1128

Max Act: 0.0630. Min Act: -0.0000

Data Index: 638904 (C4 (Web Text))

Max Activating Token Index: 732