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

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

Neuron 1810 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4305. Min Range: -3.4305

Max Act: 3.4305. Min Act: -0.0000

Data Index: 595636 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 3.4305. Min Range: -3.4305

Max Act: 2.8699. Min Act: -0.0000

Data Index: 1312927 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.7112. Min Act: -0.0000

Data Index: 1214708 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.7928. Min Act: -0.0000

Data Index: 942341 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.6852. Min Act: -0.0000

Data Index: 104050 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.6565. Min Act: -0.0000

Data Index: 79012 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.5078. Min Act: -0.0000

Data Index: 614126 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.5502. Min Act: -0.0000

Data Index: 556954 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1232137 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.6675. Min Act: -0.0000

Data Index: 673373 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.5747. Min Act: -0.0000

Data Index: 690841 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.6583. Min Act: -0.0000

Data Index: 320339 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.5350. Min Act: -0.0000

Data Index: 636759 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.3822. Min Act: -0.0000

Data Index: 1308267 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.5308. Min Act: -0.0000

Data Index: 1262271 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.4460. Min Act: -0.0000

Data Index: 768997 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.4402. Min Act: -0.0000

Data Index: 291062 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.4860. Min Act: -0.0000

Data Index: 723441 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.4019. Min Act: -0.0000

Data Index: 826859 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 3.4305. Min Range: -3.4305

Max Act: 1.4265. Min Act: -0.0000

Data Index: 1200469 (C4 (Web Text))

Max Activating Token Index: 819