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

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

Neuron 4430 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3838. Min Range: -6.3838

Max Act: 6.3838. Min Act: -0.0000

Data Index: 693749 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 6.3838. Min Range: -6.3838

Max Act: 6.2263. Min Act: -0.0000

Data Index: 1259463 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 6.3838. Min Range: -6.3838

Max Act: 5.8157. Min Act: -0.0000

Data Index: 85421 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 6.3838. Min Range: -6.3838

Max Act: 5.9752. Min Act: -0.0000

Data Index: 107502 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 6.3838. Min Range: -6.3838

Max Act: 5.6533. Min Act: -0.0000

Data Index: 1021205 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 6.3838. Min Range: -6.3838

Max Act: 5.4160. Min Act: -0.0000

Data Index: 189732 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 6.3838. Min Range: -6.3838

Max Act: 5.0896. Min Act: -0.0000

Data Index: 709038 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 6.3838. Min Range: -6.3838

Max Act: 4.5915. Min Act: -0.0000

Data Index: 737896 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 6.3838. Min Range: -6.3838

Max Act: 4.2911. Min Act: -0.0000

Data Index: 576674 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 6.3838. Min Range: -6.3838

Max Act: 4.0920. Min Act: -0.0000

Data Index: 7889 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 6.3838. Min Range: -6.3838

Max Act: 3.8450. Min Act: -0.0000

Data Index: 941467 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 6.3838. Min Range: -6.3838

Max Act: 3.8454. Min Act: -0.0000

Data Index: 423295 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 6.3838. Min Range: -6.3838

Max Act: 3.8117. Min Act: -0.0000

Data Index: 483317 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 6.3838. Min Range: -6.3838

Max Act: 3.6442. Min Act: -0.0000

Data Index: 1038541 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 6.3838. Min Range: -6.3838

Max Act: 3.7645. Min Act: -0.0000

Data Index: 734059 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 6.3838. Min Range: -6.3838

Max Act: 3.7140. Min Act: -0.0000

Data Index: 1114429 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 6.3838. Min Range: -6.3838

Max Act: 3.7021. Min Act: -0.0000

Data Index: 1025622 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 6.3838. Min Range: -6.3838

Max Act: 3.6647. Min Act: -0.0000

Data Index: 222164 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 6.3838. Min Range: -6.3838

Max Act: 3.4976. Min Act: -0.0000

Data Index: 762393 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 6.3838. Min Range: -6.3838

Max Act: 3.8085. Min Act: -0.0000

Data Index: 444544 (C4 (Web Text))

Max Activating Token Index: 583