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

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

Neuron 2130 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: 0.5785. Min Range: -0.5785

Max Act: 0.5785. Min Act: -0.0000

Data Index: 203177 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.5773. Min Act: -0.0000

Data Index: 53951 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4770. Min Act: 0.0000

Data Index: 331781 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1322018 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1301194 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4260. Min Act: -0.0000

Data Index: 64619 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4304. Min Act: -0.0000

Data Index: 734884 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4248. Min Act: -0.0000

Data Index: 997198 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1220442 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4147. Min Act: -0.0000

Data Index: 398731 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.4103. Min Act: -0.0000

Data Index: 21560 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3940. Min Act: -0.0000

Data Index: 360623 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3870. Min Act: -0.0000

Data Index: 199142 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3791. Min Act: -0.0000

Data Index: 477270 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3876. Min Act: -0.0000

Data Index: 865846 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1204442 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3505. Min Act: -0.0000

Data Index: 244647 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3604. Min Act: -0.0000

Data Index: 530593 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3596. Min Act: -0.0000

Data Index: 594135 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.5785. Min Range: -0.5785

Max Act: 0.3735. Min Act: -0.0000

Data Index: 49041 (C4 (Web Text))

Max Activating Token Index: 23