Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1244 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0806. Min Act: -0.0002

Data Index: 492276 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0822. Min Act: -0.0002

Data Index: 333500 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0802. Min Act: -0.0002

Data Index: 891558 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0834. Min Act: -0.0002

Data Index: 322052 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0733. Min Act: -0.0002

Data Index: 550134 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0743. Min Act: -0.0002

Data Index: 710246 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0779. Min Act: -0.0002

Data Index: 108542 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1204966 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0764. Min Act: -0.0002

Data Index: 14013 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0713. Min Act: -0.0002

Data Index: 426591 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0677. Min Act: -0.0002

Data Index: 782646 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0713. Min Act: -0.0002

Data Index: 204678 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1216052 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0707. Min Act: -0.0002

Data Index: 186292 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0665. Min Act: -0.0002

Data Index: 754607 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0671. Min Act: -0.0002

Data Index: 399447 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0695. Min Act: -0.0001

Data Index: 172971 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1259985 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0716. Min Act: -0.0002

Data Index: 27111 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.0834. Min Range: -0.0834

Max Act: 0.0678. Min Act: -0.0002

Data Index: 672024 (C4 (Web Text))

Max Activating Token Index: 527