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

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

Neuron 84 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: 0.1064. Min Range: -0.1064

Max Act: 0.1064. Min Act: -0.0002

Data Index: 102004 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0846. Min Act: -0.0002

Data Index: 209272 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0695. Min Act: -0.0002

Data Index: 195636 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0703. Min Act: -0.0002

Data Index: 294721 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0675. Min Act: -0.0002

Data Index: 281519 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0639. Min Act: -0.0003

Data Index: 833245 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0629. Min Act: -0.0002

Data Index: 472165 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0638. Min Act: -0.0002

Data Index: 338722 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0601. Min Act: -0.0002

Data Index: 4314 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0622. Min Act: -0.0002

Data Index: 383450 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0605. Min Act: -0.0002

Data Index: 717376 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1081201 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0603. Min Act: -0.0002

Data Index: 153443 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0593. Min Act: -0.0002

Data Index: 17610 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0566. Min Act: -0.0002

Data Index: 273670 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0585. Min Act: -0.0002

Data Index: 926586 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0553. Min Act: -0.0003

Data Index: 548757 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0577. Min Act: -0.0002

Data Index: 463282 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1222201 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0585. Min Act: -0.0003

Data Index: 343742 (C4 (Web Text))

Max Activating Token Index: 984