Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5185 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2694. Min Range: -1.2694

Max Act: 1.2694. Min Act: -0.0000

Data Index: 1156660 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 1.2694. Min Range: -1.2694

Max Act: 1.2498. Min Act: -0.0000

Data Index: 1019146 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.2694. Min Range: -1.2694

Max Act: 1.1670. Min Act: -0.0000

Data Index: 1003709 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 1.2694. Min Range: -1.2694

Max Act: 1.0411. Min Act: -0.0000

Data Index: 754501 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.2694. Min Range: -1.2694

Max Act: 1.0188. Min Act: -0.0000

Data Index: 563460 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.9219. Min Act: -0.0000

Data Index: 478960 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1300433 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.9488. Min Act: -0.0000

Data Index: 817181 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1230610 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.8679. Min Act: -0.0000

Data Index: 514989 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.8402. Min Act: -0.0000

Data Index: 762173 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.8318. Min Act: -0.0000

Data Index: 146423 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.8347. Min Act: -0.0000

Data Index: 889749 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.8260. Min Act: -0.0000

Data Index: 44089 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1321483 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.8150. Min Act: -0.0000

Data Index: 827576 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.8044. Min Act: -0.0000

Data Index: 489731 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.8051. Min Act: -0.0000

Data Index: 866769 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.7981. Min Act: -0.0000

Data Index: 273955 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 1.2694. Min Range: -1.2694

Max Act: 0.7501. Min Act: -0.0000

Data Index: 527071 (C4 (Web Text))

Max Activating Token Index: 260