Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 656 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6229. Min Act: -0.0000

Data Index: 138799 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6666. Min Act: -0.0000

Data Index: 462898 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6538. Min Act: -0.0001

Data Index: 761412 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6017. Min Act: -0.0001

Data Index: 142291 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5674. Min Act: -0.0001

Data Index: 446966 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5616. Min Act: -0.0000

Data Index: 456002 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5779. Min Act: -0.0001

Data Index: 407434 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5305. Min Act: -0.0001

Data Index: 103493 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1213097 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5199. Min Act: -0.0001

Data Index: 1143861 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1244826 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4738. Min Act: -0.0000

Data Index: 721965 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4438. Min Act: 0.0000

Data Index: 880823 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4446. Min Act: -0.0000

Data Index: 975189 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1094751 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1010379 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4284. Min Act: -0.0000

Data Index: 323715 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4495. Min Act: -0.0001

Data Index: 18445 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4125. Min Act: -0.0001

Data Index: 1035069 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4110. Min Act: -0.0001

Data Index: 1321362 (C4 (Web Text))

Max Activating Token Index: 644