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

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

Neuron 4555 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5358. Min Act: -0.0000

Data Index: 433945 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5336. Min Act: -0.0000

Data Index: 307857 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4907. Min Act: -0.0000

Data Index: 394385 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1213714 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1210798 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1214112 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4068. Min Act: -0.0000

Data Index: 877529 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4245. Min Act: -0.0000

Data Index: 900971 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4548. Min Act: -0.0000

Data Index: 135041 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1140119 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1297279 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4153. Min Act: -0.0000

Data Index: 988025 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3874. Min Act: -0.0000

Data Index: 722700 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3816. Min Act: -0.0000

Data Index: 195388 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3755. Min Act: -0.0000

Data Index: 944427 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1093571 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1206308 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3645. Min Act: -0.0000

Data Index: 955174 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.4008. Min Act: -0.0000

Data Index: 321106 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.5358. Min Range: -0.5358

Max Act: 0.3849. Min Act: -0.0000

Data Index: 580895 (C4 (Web Text))

Max Activating Token Index: 282