Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 511 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8962. Min Act: -0.0001

Data Index: 230619 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8733. Min Act: -0.0001

Data Index: 855896 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8366. Min Act: -0.0001

Data Index: 1335926 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8656. Min Act: -0.0001

Data Index: 1140650 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8111. Min Act: -0.0001

Data Index: 1098207 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8117. Min Act: -0.0001

Data Index: 1144129 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8102. Min Act: -0.0001

Data Index: 781732 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7902. Min Act: -0.0001

Data Index: 750359 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.8046. Min Act: -0.0001

Data Index: 366133 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7942. Min Act: -0.0001

Data Index: 68369 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7745. Min Act: -0.0001

Data Index: 482637 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7769. Min Act: -0.0001

Data Index: 797056 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6877. Min Act: -0.0001

Data Index: 716187 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6821. Min Act: -0.0001

Data Index: 48490 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1050998 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6921. Min Act: -0.0001

Data Index: 88771 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7668. Min Act: -0.0001

Data Index: 147986 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7385. Min Act: -0.0001

Data Index: 1232375 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.7812. Min Act: -0.0001

Data Index: 611991 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.8962. Min Range: -0.8962

Max Act: 0.6848. Min Act: -0.0001

Data Index: 943374 (C4 (Web Text))

Max Activating Token Index: 628