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

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

Neuron 528 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1065260 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.5063. Min Act: -0.0000

Data Index: 859628 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1293100 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1062460 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.4726. Min Act: -0.0000

Data Index: 802831 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.4717. Min Act: -0.0000

Data Index: 522749 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.4236. Min Act: -0.0000

Data Index: 445891 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.4297. Min Act: -0.0000

Data Index: 404550 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3849. Min Act: -0.0000

Data Index: 407365 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1310817 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3955. Min Act: -0.0000

Data Index: 76287 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1261448 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3827. Min Act: -0.0000

Data Index: 207701 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3476. Min Act: -0.0000

Data Index: 350229 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3560. Min Act: -0.0000

Data Index: 254036 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3864. Min Act: -0.0000

Data Index: 242359 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3787. Min Act: -0.0000

Data Index: 720564 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1184918 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1044567 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.5495. Min Range: -0.5495

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1137360 (C4 (Web Text))

Max Activating Token Index: 187