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

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

Neuron 638 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: 0.0928. Min Range: -0.0928

Max Act: 0.0928. Min Act: -0.0002

Data Index: 96097 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0916. Min Act: -0.0002

Data Index: 598850 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0910. Min Act: -0.0002

Data Index: 444732 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0878. Min Act: -0.0002

Data Index: 198840 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0887. Min Act: -0.0002

Data Index: 266755 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0900. Min Act: -0.0002

Data Index: 976066 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0859. Min Act: -0.0002

Data Index: 542513 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0921. Min Act: -0.0002

Data Index: 1053152 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0793. Min Act: -0.0002

Data Index: 677414 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1176460 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0768. Min Act: -0.0002

Data Index: 488493 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1329084 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0775. Min Act: -0.0002

Data Index: 158337 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0894. Min Act: -0.0002

Data Index: 725094 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1252975 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0797. Min Act: -0.0002

Data Index: 94720 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1374434 (Python Code)

Max Activating Token Index: 229

Text #17

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0725. Min Act: -0.0002

Data Index: 845864 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1086562 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0731. Min Act: -0.0002

Data Index: 925798 (C4 (Web Text))

Max Activating Token Index: 438