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

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

Neuron 3768 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.9250. Min Act: -0.0000

Data Index: 604117 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.8815. Min Act: -0.0000

Data Index: 999437 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.8790. Min Act: -0.0000

Data Index: 48638 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7976. Min Act: -0.0000

Data Index: 681055 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.8097. Min Act: -0.0000

Data Index: 808899 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7601. Min Act: -0.0000

Data Index: 16703 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.7067. Min Act: -0.0000

Data Index: 778197 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6647. Min Act: -0.0000

Data Index: 526878 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6471. Min Act: -0.0000

Data Index: 941396 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.5776. Min Act: -0.0000

Data Index: 553889 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6139. Min Act: -0.0000

Data Index: 1297311 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1243769 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.5991. Min Act: -0.0000

Data Index: 396712 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.5804. Min Act: -0.0000

Data Index: 633524 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.5480. Min Act: -0.0000

Data Index: 594713 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.5543. Min Act: -0.0000

Data Index: 751186 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1046127 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1257407 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.5212. Min Act: -0.0000

Data Index: 989762 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.9250. Min Range: -0.9250

Max Act: 0.5260. Min Act: -0.0000

Data Index: 618313 (C4 (Web Text))

Max Activating Token Index: 467