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

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

Neuron 1405 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: 0.0957. Min Range: -0.0957

Max Act: 0.0948. Min Act: -0.0002

Data Index: 229867 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0957. Min Act: -0.0002

Data Index: 300441 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0945. Min Act: -0.0002

Data Index: 372833 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0900. Min Act: -0.0002

Data Index: 914122 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0885. Min Act: -0.0002

Data Index: 688246 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0902. Min Act: -0.0002

Data Index: 41188 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0829. Min Act: -0.0002

Data Index: 925255 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0755. Min Act: -0.0002

Data Index: 791401 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1091750 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0764. Min Act: -0.0002

Data Index: 586007 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0787. Min Act: -0.0002

Data Index: 789774 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0786. Min Act: -0.0002

Data Index: 58766 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0663. Min Act: -0.0002

Data Index: 955609 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0736. Min Act: -0.0002

Data Index: 494798 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1272968 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1138790 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0761. Min Act: -0.0002

Data Index: 304314 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0739. Min Act: -0.0002

Data Index: 334967 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1358580 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1258197 (C4 (Web Text))

Max Activating Token Index: 847