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

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

Neuron 517 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: 0.1003. Min Range: -0.1003

Max Act: 0.1003. Min Act: -0.0002

Data Index: 78932 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0975. Min Act: -0.0002

Data Index: 644209 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0864. Min Act: -0.0002

Data Index: 55290 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1229857 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0846. Min Act: -0.0002

Data Index: 791065 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1038035 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1060960 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0845. Min Act: -0.0002

Data Index: 849644 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0873. Min Act: -0.0002

Data Index: 415820 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0834. Min Act: -0.0002

Data Index: 673110 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1094605 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0833. Min Act: -0.0002

Data Index: 706516 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1068810 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1201108 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0771. Min Act: -0.0001

Data Index: 282618 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0784. Min Act: -0.0002

Data Index: 880679 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0782. Min Act: -0.0002

Data Index: 666579 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0783. Min Act: -0.0002

Data Index: 385615 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0787. Min Act: -0.0002

Data Index: 441836 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.1003. Min Range: -0.1003

Max Act: 0.0762. Min Act: -0.0002

Data Index: 905484 (C4 (Web Text))

Max Activating Token Index: 632