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

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

Neuron 3509 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0016. Min Range: -3.0016

Max Act: 3.0016. Min Act: -0.0001

Data Index: 72730 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.5917. Min Act: -0.0001

Data Index: 15885 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.5205. Min Act: -0.0001

Data Index: 264374 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.4900. Min Act: -0.0001

Data Index: 533273 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.4532. Min Act: -0.0000

Data Index: 282468 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.0346. Min Act: -0.0001

Data Index: 38209 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.2937. Min Act: -0.0000

Data Index: 364983 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 3.0016. Min Range: -3.0016

Max Act: 1.9626. Min Act: -0.0000

Data Index: 317097 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.0586. Min Act: -0.0001

Data Index: 386963 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.0321. Min Act: -0.0001

Data Index: 1025593 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 3.0016. Min Range: -3.0016

Max Act: 1.9990. Min Act: -0.0001

Data Index: 369517 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.0987. Min Act: -0.0000

Data Index: 1153 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 3.0016. Min Range: -3.0016

Max Act: 1.9639. Min Act: -0.0001

Data Index: 945543 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 3.0016. Min Range: -3.0016

Max Act: 1.9223. Min Act: -0.0000

Data Index: 388147 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 3.0016. Min Range: -3.0016

Max Act: 2.0116. Min Act: -0.0001

Data Index: 29622 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 3.0016. Min Range: -3.0016

Max Act: 1.9633. Min Act: -0.0001

Data Index: 385624 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 3.0016. Min Range: -3.0016

Max Act: 1.8053. Min Act: -0.0001

Data Index: 825154 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 3.0016. Min Range: -3.0016

Max Act: 1.9470. Min Act: -0.0001

Data Index: 399831 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 3.0016. Min Range: -3.0016

Max Act: 1.8405. Min Act: -0.0001

Data Index: 1355180 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 3.0016. Min Range: -3.0016

Max Act: 1.6264. Min Act: -0.0000

Data Index: 1050812 (C4 (Web Text))

Max Activating Token Index: 799