Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5076 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0002

Data Index: 29250 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0843. Min Act: -0.0002

Data Index: 972048 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1287155 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1273154 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0800. Min Act: -0.0002

Data Index: 785634 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0801. Min Act: -0.0002

Data Index: 175171 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1186054 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0723. Min Act: -0.0002

Data Index: 725660 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1172301 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0780. Min Act: -0.0002

Data Index: 8165 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0714. Min Act: -0.0002

Data Index: 655911 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0745. Min Act: -0.0002

Data Index: 834423 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0729. Min Act: -0.0002

Data Index: 548360 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0698. Min Act: -0.0002

Data Index: 517612 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0646. Min Act: -0.0002

Data Index: 918085 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0671. Min Act: -0.0002

Data Index: 89391 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0665. Min Act: -0.0002

Data Index: 299030 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0580. Min Act: -0.0002

Data Index: 355439 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0656. Min Act: -0.0002

Data Index: 169078 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0674. Min Act: -0.0002

Data Index: 334180 (C4 (Web Text))

Max Activating Token Index: 717