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

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

Neuron 3270 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.5380. Min Act: -0.0000

Data Index: 46810 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.1371. Min Act: -0.0000

Data Index: 238612 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.1052. Min Act: -0.0000

Data Index: 206430 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1070681 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.0594. Min Act: -0.0000

Data Index: 822554 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.0028. Min Act: -0.0000

Data Index: 557188 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.9911. Min Act: -0.0000

Data Index: 997385 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.5380. Min Range: -1.5380

Max Act: 1.0113. Min Act: -0.0000

Data Index: 888865 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.9083. Min Act: -0.0000

Data Index: 640845 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1124048 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1135163 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.8597. Min Act: -0.0000

Data Index: 821501 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.9089. Min Act: -0.0000

Data Index: 128616 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.8723. Min Act: -0.0000

Data Index: 133483 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.8610. Min Act: -0.0000

Data Index: 680804 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.8331. Min Act: -0.0000

Data Index: 1008859 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.8589. Min Act: -0.0000

Data Index: 625630 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1341570 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.8357. Min Act: -0.0000

Data Index: 542729 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 1.5380. Min Range: -1.5380

Max Act: 0.8512. Min Act: -0.0000

Data Index: 770173 (C4 (Web Text))

Max Activating Token Index: 123