Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3854 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0897. Min Act: -0.0000

Data Index: 644829 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1151915 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0869. Min Act: -0.0000

Data Index: 145825 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0739. Min Act: -0.0000

Data Index: 829394 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1175756 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0705. Min Act: -0.0000

Data Index: 868326 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0661. Min Act: -0.0000

Data Index: 695192 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0630. Min Act: -0.0000

Data Index: 465204 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1199341 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0657. Min Act: -0.0000

Data Index: 995915 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1324196 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1305276 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0642. Min Act: -0.0000

Data Index: 119502 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0663. Min Act: -0.0000

Data Index: 831403 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0643. Min Act: -0.0000

Data Index: 969086 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0616. Min Act: -0.0000

Data Index: 829328 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0633. Min Act: -0.0000

Data Index: 855202 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0659. Min Act: -0.0000

Data Index: 784754 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0628. Min Act: -0.0000

Data Index: 708849 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0522. Min Act: -0.0000

Data Index: 1303699 (C4 (Web Text))

Max Activating Token Index: 323