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

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

Neuron 4717 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: 2.4888. Min Range: -2.4888

Max Act: 2.4761. Min Act: -0.0000

Data Index: 95903 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 2.4888. Min Range: -2.4888

Max Act: 2.4888. Min Act: -0.0000

Data Index: 190502 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 2.4888. Min Range: -2.4888

Max Act: 2.3125. Min Act: -0.0000

Data Index: 885522 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 2.4888. Min Range: -2.4888

Max Act: 2.2786. Min Act: -0.0000

Data Index: 349982 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 2.4888. Min Range: -2.4888

Max Act: 2.2269. Min Act: -0.0000

Data Index: 1248655 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 2.4888. Min Range: -2.4888

Max Act: 2.1816. Min Act: -0.0000

Data Index: 1148027 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.9637. Min Act: -0.0000

Data Index: 1240463 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.8520. Min Act: -0.0000

Data Index: 845426 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.9219. Min Act: -0.0000

Data Index: 768824 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.8898. Min Act: -0.0000

Data Index: 15085 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.8913. Min Act: -0.0000

Data Index: 1299162 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 2.4888. Min Range: -2.4888

Max Act: 2.0015. Min Act: -0.0000

Data Index: 974589 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.8764. Min Act: -0.0000

Data Index: 505513 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.8698. Min Act: -0.0000

Data Index: 346628 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.9245. Min Act: -0.0000

Data Index: 887862 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.7811. Min Act: -0.0000

Data Index: 1093697 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.6562. Min Act: -0.0000

Data Index: 805690 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.7454. Min Act: -0.0000

Data Index: 477497 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.7519. Min Act: -0.0000

Data Index: 789120 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 2.4888. Min Range: -2.4888

Max Act: 1.7317. Min Act: -0.0000

Data Index: 378904 (C4 (Web Text))

Max Activating Token Index: 586