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

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

Neuron 3571 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.6516. Min Range: -6.6516

Max Act: 6.6516. Min Act: -0.0000

Data Index: 295045 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 6.6516. Min Range: -6.6516

Max Act: 5.3039. Min Act: -0.0000

Data Index: 664115 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 6.6516. Min Range: -6.6516

Max Act: 4.4254. Min Act: -0.0000

Data Index: 1087017 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 6.6516. Min Range: -6.6516

Max Act: 4.5822. Min Act: -0.0000

Data Index: 584973 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 6.6516. Min Range: -6.6516

Max Act: 4.3778. Min Act: -0.0000

Data Index: 247523 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.8420. Min Act: -0.0000

Data Index: 214157 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.9851. Min Act: -0.0000

Data Index: 297213 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.7269. Min Act: -0.0000

Data Index: 210768 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.9172. Min Act: -0.0000

Data Index: 299688 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.9201. Min Act: -0.0000

Data Index: 980893 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.7049. Min Act: -0.0000

Data Index: 900971 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.7008. Min Act: -0.0000

Data Index: 266067 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.7687. Min Act: -0.0000

Data Index: 179871 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.7641. Min Act: -0.0000

Data Index: 1289442 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.7835. Min Act: -0.0000

Data Index: 1077525 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.7557. Min Act: -0.0000

Data Index: 1285201 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.7567. Min Act: -0.0000

Data Index: 573303 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.6794. Min Act: -0.0000

Data Index: 722144 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.6877. Min Act: -0.0000

Data Index: 503433 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 6.6516. Min Range: -6.6516

Max Act: 3.6451. Min Act: -0.0000

Data Index: 78850 (C4 (Web Text))

Max Activating Token Index: 352