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

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

Neuron 2866 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0966. Min Act: -0.0002

Data Index: 37797 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0986. Min Act: -0.0003

Data Index: 770249 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0938. Min Act: -0.0003

Data Index: 322905 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0947. Min Act: -0.0003

Data Index: 619715 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0906. Min Act: -0.0002

Data Index: 680107 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0924. Min Act: -0.0003

Data Index: 80471 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0923. Min Act: -0.0002

Data Index: 634369 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0868. Min Act: -0.0002

Data Index: 618212 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0889. Min Act: -0.0003

Data Index: 648800 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0860. Min Act: -0.0003

Data Index: 969967 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0862. Min Act: -0.0003

Data Index: 652861 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0865. Min Act: -0.0002

Data Index: 34447 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0850. Min Act: -0.0003

Data Index: 1100008 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0876. Min Act: -0.0003

Data Index: 628300 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0811. Min Act: -0.0003

Data Index: 154374 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0806. Min Act: -0.0003

Data Index: 654444 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0840. Min Act: -0.0002

Data Index: 999869 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0826. Min Act: -0.0003

Data Index: 845534 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0844. Min Act: -0.0003

Data Index: 996301 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0782. Min Act: -0.0003

Data Index: 1218809 (C4 (Web Text))

Max Activating Token Index: 488