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

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

Neuron 893 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5636. Min Act: -0.0001

Data Index: 539153 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5779. Min Act: -0.0001

Data Index: 406347 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5882. Min Act: -0.0001

Data Index: 445041 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5546. Min Act: -0.0001

Data Index: 262522 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5625. Min Act: -0.0001

Data Index: 1000718 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5228. Min Act: -0.0001

Data Index: 586458 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5375. Min Act: -0.0001

Data Index: 595054 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5084. Min Act: -0.0001

Data Index: 387694 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4886. Min Act: -0.0001

Data Index: 500314 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4862. Min Act: -0.0001

Data Index: 876492 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4859. Min Act: -0.0001

Data Index: 944513 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5419. Min Act: -0.0001

Data Index: 38773 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5095. Min Act: -0.0001

Data Index: 671281 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5159. Min Act: -0.0001

Data Index: 729541 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5109. Min Act: -0.0001

Data Index: 1268769 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4471. Min Act: -0.0001

Data Index: 722817 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4874. Min Act: -0.0001

Data Index: 668568 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4562. Min Act: -0.0001

Data Index: 335323 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5155. Min Act: -0.0001

Data Index: 1019212 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4864. Min Act: -0.0001

Data Index: 992987 (C4 (Web Text))

Max Activating Token Index: 391