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

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

Neuron 1711 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: 0.0948. Min Range: -0.0948

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1443741 (Python Code)

Max Activating Token Index: 480

Text #1

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1424956 (Python Code)

Max Activating Token Index: 231

Text #2

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1644789 (Python Code)

Max Activating Token Index: 1012

Text #3

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0893. Min Act: -0.0002

Data Index: 689818 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0872. Min Act: -0.0002

Data Index: 193852 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1510047 (Python Code)

Max Activating Token Index: 709

Text #6

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0852. Min Act: -0.0002

Data Index: 269097 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1062571 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1439264 (Python Code)

Max Activating Token Index: 740

Text #9

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1040255 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0816. Min Act: -0.0002

Data Index: 429009 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0769. Min Act: -0.0002

Data Index: 493574 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1410589 (Python Code)

Max Activating Token Index: 662

Text #13

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0780. Min Act: -0.0002

Data Index: 835460 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0813. Min Act: -0.0002

Data Index: 598323 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0780. Min Act: -0.0002

Data Index: 901303 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1009756 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0767. Min Act: -0.0002

Data Index: 443524 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0750. Min Act: -0.0002

Data Index: 977201 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0744. Min Act: -0.0002

Data Index: 602087 (C4 (Web Text))

Max Activating Token Index: 898