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

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

Neuron 3796 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.6139. Min Act: -0.0000

Data Index: 63779 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5699. Min Act: -0.0000

Data Index: 639890 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5430. Min Act: -0.0000

Data Index: 738341 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5040. Min Act: -0.0000

Data Index: 302235 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5189. Min Act: -0.0000

Data Index: 444091 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4993. Min Act: -0.0000

Data Index: 603252 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1062638 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.5112. Min Act: -0.0000

Data Index: 438868 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4934. Min Act: 0.0001

Data Index: 7119 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4713. Min Act: 0.0000

Data Index: 129839 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4865. Min Act: 0.0000

Data Index: 822536 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1254978 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4797. Min Act: 0.0000

Data Index: 537876 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4782. Min Act: -0.0000

Data Index: 471958 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4575. Min Act: -0.0000

Data Index: 792631 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4633. Min Act: -0.0000

Data Index: 831139 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4574. Min Act: -0.0000

Data Index: 87099 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4404. Min Act: -0.0000

Data Index: 322319 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1331660 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.6139. Min Range: -0.6139

Max Act: 0.4706. Min Act: 0.0000

Data Index: 1328387 (C4 (Web Text))

Max Activating Token Index: 342