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

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

Neuron 2386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2716. Min Range: -2.2716

Max Act: 2.2716. Min Act: -0.0000

Data Index: 441387 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 2.2716. Min Range: -2.2716

Max Act: 2.2069. Min Act: -0.0000

Data Index: 1093300 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 2.2716. Min Range: -2.2716

Max Act: 2.1499. Min Act: -0.0000

Data Index: 80864 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.6597. Min Act: -0.0000

Data Index: 41026 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.6699. Min Act: -0.0000

Data Index: 429640 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.8024. Min Act: -0.0000

Data Index: 63461 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.6241. Min Act: -0.0000

Data Index: 324934 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.5885. Min Act: -0.0000

Data Index: 733372 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.2997. Min Act: -0.0000

Data Index: 653903 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.4604. Min Act: -0.0000

Data Index: 349933 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.5368. Min Act: -0.0000

Data Index: 192137 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.6047. Min Act: -0.0000

Data Index: 34117 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.5251. Min Act: -0.0000

Data Index: 607603 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.7818. Min Act: -0.0000

Data Index: 74147 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.4488. Min Act: -0.0000

Data Index: 702829 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.4138. Min Act: -0.0000

Data Index: 252895 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.5264. Min Act: -0.0000

Data Index: 851585 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.4349. Min Act: -0.0000

Data Index: 640812 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.4136. Min Act: -0.0000

Data Index: 823974 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 2.2716. Min Range: -2.2716

Max Act: 1.4894. Min Act: -0.0000

Data Index: 781506 (C4 (Web Text))

Max Activating Token Index: 1018