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

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

Neuron 5752 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1330801 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0917. Min Act: -0.0000

Data Index: 104276 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1416486 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1617011 (Python Code)

Max Activating Token Index: 328

Text #4

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0909. Min Act: -0.0000

Data Index: 653568 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1008818 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0866. Min Act: -0.0000

Data Index: 191227 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1001907 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1529045 (Python Code)

Max Activating Token Index: 796

Text #9

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0781. Min Act: -0.0000

Data Index: 120852 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1507548 (Python Code)

Max Activating Token Index: 700

Text #11

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1362595 (Python Code)

Max Activating Token Index: 1004

Text #12

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0832. Min Act: -0.0000

Data Index: 171493 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0789. Min Act: -0.0000

Data Index: 520283 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0817. Min Act: -0.0000

Data Index: 995626 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1550028 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0780. Min Act: -0.0000

Data Index: 1489349 (Python Code)

Max Activating Token Index: 1000

Text #17

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0737. Min Act: -0.0000

Data Index: 379685 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1498985 (Python Code)

Max Activating Token Index: 796

Text #19

Max Range: 0.1124. Min Range: -0.1124

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1368936 (Python Code)

Max Activating Token Index: 960