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

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

Neuron 2724 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.9699. Min Act: 0.0000

Data Index: 701670 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8202. Min Act: -0.0000

Data Index: 539683 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8357. Min Act: 0.0000

Data Index: 671537 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.8009. Min Act: -0.0000

Data Index: 636587 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.7598. Min Act: -0.0000

Data Index: 27941 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.7058. Min Act: -0.0000

Data Index: 428116 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1020838 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.7026. Min Act: -0.0000

Data Index: 653523 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.6945. Min Act: -0.0000

Data Index: 897139 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.7114. Min Act: 0.0001

Data Index: 283350 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.6688. Min Act: -0.0000

Data Index: 997058 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.6844. Min Act: -0.0000

Data Index: 556030 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1163075 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1729 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.6719. Min Act: -0.0000

Data Index: 297314 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.6797. Min Act: 0.0000

Data Index: 1045113 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.6623. Min Act: -0.0000

Data Index: 129470 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.6400. Min Act: -0.0000

Data Index: 712991 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.6426. Min Act: -0.0000

Data Index: 721918 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.9699. Min Range: -0.9699

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1211349 (C4 (Web Text))

Max Activating Token Index: 603