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

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

Neuron 713 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0710. Min Range: -1.0710

Max Act: 1.0710. Min Act: -0.0001

Data Index: 105123 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 1.0710. Min Range: -1.0710

Max Act: 1.0094. Min Act: -0.0001

Data Index: 273927 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9733. Min Act: -0.0001

Data Index: 261230 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 1.0710. Min Range: -1.0710

Max Act: 1.0089. Min Act: -0.0001

Data Index: 911427 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 1.0710. Min Range: -1.0710

Max Act: 1.0289. Min Act: -0.0001

Data Index: 89276 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9627. Min Act: -0.0001

Data Index: 986773 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9195. Min Act: -0.0001

Data Index: 1156675 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.0710. Min Range: -1.0710

Max Act: 1.0031. Min Act: -0.0001

Data Index: 6549 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9600. Min Act: -0.0001

Data Index: 119757 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.7906. Min Act: -0.0001

Data Index: 934238 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8943. Min Act: -0.0001

Data Index: 1266835 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9217. Min Act: -0.0001

Data Index: 214423 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9423. Min Act: -0.0001

Data Index: 21258 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8742. Min Act: -0.0001

Data Index: 141187 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8722. Min Act: -0.0001

Data Index: 1081404 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8980. Min Act: -0.0001

Data Index: 1046531 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.9059. Min Act: -0.0001

Data Index: 1216738 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8429. Min Act: -0.0001

Data Index: 894731 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8904. Min Act: -0.0001

Data Index: 324980 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 1.0710. Min Range: -1.0710

Max Act: 0.8522. Min Act: -0.0001

Data Index: 741977 (C4 (Web Text))

Max Activating Token Index: 693