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

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

Neuron 3867 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.9920. Min Act: -0.0002

Data Index: 472142 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.8289. Min Act: -0.0002

Data Index: 192785 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.8063. Min Act: -0.0002

Data Index: 333818 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7529. Min Act: -0.0002

Data Index: 875116 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7917. Min Act: -0.0002

Data Index: 203166 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7489. Min Act: -0.0002

Data Index: 890733 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7469. Min Act: -0.0002

Data Index: 992971 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7240. Min Act: -0.0002

Data Index: 1108471 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7213. Min Act: -0.0002

Data Index: 402671 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7056. Min Act: -0.0002

Data Index: 1014516 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7488. Min Act: -0.0002

Data Index: 179622 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7225. Min Act: -0.0002

Data Index: 52632 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6490. Min Act: -0.0002

Data Index: 1261454 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6665. Min Act: -0.0002

Data Index: 1314801 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7500. Min Act: -0.0002

Data Index: 844161 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6597. Min Act: -0.0002

Data Index: 487762 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7010. Min Act: -0.0002

Data Index: 465726 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7434. Min Act: -0.0002

Data Index: 140588 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7010. Min Act: -0.0002

Data Index: 16580 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7379. Min Act: -0.0002

Data Index: 263852 (C4 (Web Text))

Max Activating Token Index: 977