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

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

Neuron 3696 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.8565. Min Act: -0.0000

Data Index: 770211 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.6968. Min Act: -0.0000

Data Index: 317780 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.6662. Min Act: -0.0000

Data Index: 80867 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.4908. Min Act: -0.0000

Data Index: 490769 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.4868. Min Act: -0.0000

Data Index: 892972 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.4869. Min Act: -0.0000

Data Index: 216201 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.4317. Min Act: -0.0000

Data Index: 757975 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.3529. Min Act: -0.0000

Data Index: 850218 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.3187. Min Act: -0.0000

Data Index: 600373 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.2838. Min Act: -0.0000

Data Index: 757811 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.5254. Min Act: -0.0000

Data Index: 962599 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.4636. Min Act: -0.0000

Data Index: 155641 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.4048. Min Act: -0.0000

Data Index: 1016009 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.3679. Min Act: -0.0000

Data Index: 1217699 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.3399. Min Act: -0.0000

Data Index: 131578 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.3282. Min Act: -0.0000

Data Index: 949479 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.3477. Min Act: -0.0000

Data Index: 798015 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.3365. Min Act: -0.0000

Data Index: 89898 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.2529. Min Act: -0.0000

Data Index: 1352496 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 2.8565. Min Range: -2.8565

Max Act: 2.0739. Min Act: -0.0000

Data Index: 321155 (C4 (Web Text))

Max Activating Token Index: 120