Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1670 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.9668. Min Act: -0.0001

Data Index: 557154 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.7524. Min Act: -0.0001

Data Index: 765702 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.6207. Min Act: -0.0001

Data Index: 1035079 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4842. Min Act: -0.0001

Data Index: 146147 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4376. Min Act: -0.0001

Data Index: 687568 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4664. Min Act: -0.0001

Data Index: 548406 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.5261. Min Act: -0.0001

Data Index: 616822 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4705. Min Act: -0.0001

Data Index: 369529 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.3916. Min Act: -0.0001

Data Index: 35741 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4758. Min Act: -0.0001

Data Index: 683761 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.3781. Min Act: -0.0001

Data Index: 1245993 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.5193. Min Act: -0.0001

Data Index: 1107757 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4896. Min Act: -0.0001

Data Index: 1030770 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.5184. Min Act: -0.0001

Data Index: 1171509 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.6201. Min Act: -0.0001

Data Index: 620810 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.2780. Min Act: -0.0001

Data Index: 1345041 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4346. Min Act: -0.0001

Data Index: 288571 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.3467. Min Act: -0.0001

Data Index: 747333 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.3036. Min Act: -0.0001

Data Index: 273174 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.3679. Min Act: -0.0001

Data Index: 697343 (C4 (Web Text))

Max Activating Token Index: 438