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

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

Neuron 4104 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.1020. Min Act: -0.0002

Data Index: 77154 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0936. Min Act: -0.0002

Data Index: 404296 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0995. Min Act: -0.0002

Data Index: 629154 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0953. Min Act: -0.0002

Data Index: 701721 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1122812 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0861. Min Act: -0.0002

Data Index: 392386 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0837. Min Act: -0.0002

Data Index: 246921 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0837. Min Act: -0.0002

Data Index: 862206 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0781. Min Act: -0.0002

Data Index: 70414 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0819. Min Act: -0.0002

Data Index: 987438 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1306704 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0842. Min Act: -0.0002

Data Index: 700619 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0793. Min Act: -0.0002

Data Index: 400486 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0788. Min Act: -0.0002

Data Index: 541247 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0817. Min Act: -0.0002

Data Index: 247113 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0786. Min Act: -0.0002

Data Index: 792515 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0784. Min Act: -0.0002

Data Index: 317150 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0754. Min Act: -0.0002

Data Index: 388931 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1101567 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0767. Min Act: -0.0002

Data Index: 980011 (C4 (Web Text))

Max Activating Token Index: 487