Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1048 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.9261. Min Act: -0.0000

Data Index: 921318 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8694. Min Act: -0.0000

Data Index: 500437 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8707. Min Act: -0.0000

Data Index: 550439 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8812. Min Act: -0.0000

Data Index: 687617 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8559. Min Act: -0.0000

Data Index: 936123 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1007110 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8399. Min Act: -0.0001

Data Index: 1276197 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8245. Min Act: -0.0000

Data Index: 408155 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7901. Min Act: -0.0000

Data Index: 406135 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1255091 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7998. Min Act: -0.0001

Data Index: 307119 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7714. Min Act: -0.0000

Data Index: 238573 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7488. Min Act: -0.0001

Data Index: 773271 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7695. Min Act: -0.0000

Data Index: 965736 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7674. Min Act: -0.0000

Data Index: 107422 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7599. Min Act: -0.0000

Data Index: 103884 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1204121 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7445. Min Act: -0.0000

Data Index: 803429 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7151. Min Act: -0.0000

Data Index: 281908 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7355. Min Act: -0.0000

Data Index: 461135 (C4 (Web Text))

Max Activating Token Index: 436