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

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

Neuron 4907 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1263. Min Act: -0.0001

Data Index: 72589 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1099. Min Act: -0.0001

Data Index: 820638 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1290450 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0915. Min Act: -0.0001

Data Index: 664672 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1091301 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0859. Min Act: -0.0001

Data Index: 441617 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0940. Min Act: -0.0001

Data Index: 172391 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0839. Min Act: -0.0001

Data Index: 233539 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0756. Min Act: -0.0001

Data Index: 255468 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1483548 (Python Code)

Max Activating Token Index: 320

Text #10

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1086819 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0863. Min Act: -0.0001

Data Index: 156908 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0794. Min Act: -0.0001

Data Index: 773328 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0841. Min Act: -0.0001

Data Index: 246786 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0941. Min Act: -0.0001

Data Index: 306293 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0806. Min Act: -0.0001

Data Index: 147537 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1064970 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1219444 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0791. Min Act: -0.0001

Data Index: 389725 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0745. Min Act: -0.0001

Data Index: 972633 (C4 (Web Text))

Max Activating Token Index: 405