Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1617 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0887. Min Act: -0.0002

Data Index: 901797 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0924. Min Act: -0.0002

Data Index: 190283 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1468575 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0784. Min Act: -0.0002

Data Index: 338836 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0790. Min Act: -0.0002

Data Index: 418730 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1274164 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1041514 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0787. Min Act: -0.0002

Data Index: 491724 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0713. Min Act: -0.0002

Data Index: 322657 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1130340 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0711. Min Act: -0.0002

Data Index: 726932 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0762. Min Act: -0.0002

Data Index: 330025 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0773. Min Act: -0.0002

Data Index: 278772 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1100686 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0657. Min Act: -0.0001

Data Index: 888426 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0761. Min Act: -0.0002

Data Index: 108057 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1026248 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0706. Min Act: -0.0002

Data Index: 400223 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1153787 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1305790 (C4 (Web Text))

Max Activating Token Index: 243