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

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

Neuron 4739 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.8696. Min Act: -0.0000

Data Index: 313592 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.6964. Min Act: -0.0000

Data Index: 681087 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.6213. Min Act: -0.0000

Data Index: 72711 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.7445. Min Act: -0.0000

Data Index: 5947 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.7225. Min Act: -0.0000

Data Index: 1107898 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.6695. Min Act: -0.0000

Data Index: 1228267 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.5608. Min Act: -0.0000

Data Index: 867117 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.6414. Min Act: -0.0000

Data Index: 1268474 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.6452. Min Act: -0.0000

Data Index: 165006 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.5811. Min Act: -0.0000

Data Index: 362642 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.5713. Min Act: -0.0000

Data Index: 601168 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.7072. Min Act: -0.0000

Data Index: 942033 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.6580. Min Act: -0.0000

Data Index: 1272686 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.5164. Min Act: -0.0000

Data Index: 698895 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.5496. Min Act: -0.0000

Data Index: 1198868 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.5874. Min Act: -0.0000

Data Index: 713696 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.5407. Min Act: -0.0000

Data Index: 27813 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.5825. Min Act: -0.0000

Data Index: 1353654 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.5247. Min Act: -0.0000

Data Index: 1247676 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 1.8696. Min Range: -1.8696

Max Act: 1.5239. Min Act: -0.0000

Data Index: 371328 (C4 (Web Text))

Max Activating Token Index: 252