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

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

Neuron 223 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.7759. Min Act: -0.0000

Data Index: 811357 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.7001. Min Act: -0.0000

Data Index: 131922 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.8157. Min Act: -0.0000

Data Index: 792536 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.7889. Min Act: -0.0000

Data Index: 108099 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.8840. Min Act: -0.0000

Data Index: 1116310 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.7651. Min Act: -0.0000

Data Index: 130345 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.6789. Min Act: -0.0000

Data Index: 222948 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.9594. Min Act: -0.0000

Data Index: 144441 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.6736. Min Act: -0.0000

Data Index: 1261481 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.8347. Min Act: -0.0000

Data Index: 1140455 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.9615. Min Act: -0.0000

Data Index: 181671 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.9661. Min Act: -0.0000

Data Index: 357801 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.9117. Min Act: -0.0000

Data Index: 323939 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 2.0641. Min Range: -2.0641

Max Act: 2.0641. Min Act: -0.0000

Data Index: 159221 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.8004. Min Act: -0.0000

Data Index: 217711 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.7872. Min Act: -0.0000

Data Index: 107759 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.7151. Min Act: -0.0000

Data Index: 446138 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.8847. Min Act: -0.0000

Data Index: 1188223 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.7757. Min Act: -0.0000

Data Index: 454742 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 2.0641. Min Range: -2.0641

Max Act: 1.8806. Min Act: -0.0000

Data Index: 679329 (C4 (Web Text))

Max Activating Token Index: 830