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

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

Neuron 1000 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: 1.3082. Min Range: -1.3082

Max Act: 1.3082. Min Act: -0.0000

Data Index: 1021558 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.1748. Min Act: -0.0000

Data Index: 1116796 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.1303. Min Act: -0.0000

Data Index: 248812 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1144290 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.9713. Min Act: -0.0000

Data Index: 467703 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0253. Min Act: -0.0000

Data Index: 831112 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.9000. Min Act: -0.0000

Data Index: 586630 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.9209. Min Act: -0.0000

Data Index: 691975 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1255402 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.9828. Min Act: -0.0000

Data Index: 246927 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.9103. Min Act: -0.0000

Data Index: 851856 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.9043. Min Act: -0.0000

Data Index: 826623 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 1.3082. Min Range: -1.3082

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1014020 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.8821. Min Act: -0.0000

Data Index: 101571 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.8141. Min Act: -0.0000

Data Index: 578919 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.8375. Min Act: -0.0000

Data Index: 310145 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.8546. Min Act: -0.0000

Data Index: 287185 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.7854. Min Act: -0.0000

Data Index: 124085 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.7964. Min Act: -0.0000

Data Index: 1236324 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.3082. Min Range: -1.3082

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1146829 (C4 (Web Text))

Max Activating Token Index: 878