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

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

Neuron 1698 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8887. Min Act: -0.0001

Data Index: 137107 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.9031. Min Act: -0.0001

Data Index: 834158 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8929. Min Act: -0.0001

Data Index: 836733 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8500. Min Act: -0.0001

Data Index: 786999 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8265. Min Act: -0.0001

Data Index: 784174 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7576. Min Act: -0.0001

Data Index: 641233 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8211. Min Act: -0.0001

Data Index: 1012917 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7596. Min Act: -0.0001

Data Index: 402625 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7324. Min Act: -0.0001

Data Index: 682020 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7339. Min Act: -0.0001

Data Index: 84764 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7218. Min Act: -0.0001

Data Index: 473207 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7710. Min Act: -0.0001

Data Index: 146071 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7052. Min Act: -0.0001

Data Index: 87549 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7018. Min Act: -0.0001

Data Index: 163143 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7260. Min Act: -0.0001

Data Index: 1112153 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7120. Min Act: -0.0001

Data Index: 303379 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7384. Min Act: -0.0001

Data Index: 1028099 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7938. Min Act: -0.0001

Data Index: 234693 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6903. Min Act: -0.0001

Data Index: 312289 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6889. Min Act: -0.0001

Data Index: 594478 (C4 (Web Text))

Max Activating Token Index: 37