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

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

Neuron 3457 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0982. Min Act: -0.0002

Data Index: 600419 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0982. Min Act: -0.0002

Data Index: 793976 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1055193 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0968. Min Act: -0.0002

Data Index: 32314 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1072593 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0903. Min Act: -0.0002

Data Index: 903867 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0896. Min Act: -0.0002

Data Index: 597564 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1137715 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0921. Min Act: -0.0002

Data Index: 383843 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1228781 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1258060 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0835. Min Act: -0.0002

Data Index: 378665 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0769. Min Act: -0.0002

Data Index: 597239 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0880. Min Act: -0.0002

Data Index: 797629 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0813. Min Act: -0.0002

Data Index: 742760 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0810. Min Act: -0.0002

Data Index: 688497 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0789. Min Act: -0.0002

Data Index: 290064 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0866. Min Act: -0.0002

Data Index: 168402 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0871. Min Act: -0.0002

Data Index: 374463 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0819. Min Act: -0.0002

Data Index: 225610 (C4 (Web Text))

Max Activating Token Index: 195