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

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

Neuron 1896 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0603. Min Act: -0.0003

Data Index: 241453 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1311589 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0528. Min Act: -0.0003

Data Index: 484645 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0487. Min Act: -0.0003

Data Index: 188187 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0476. Min Act: -0.0003

Data Index: 952818 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0508. Min Act: -0.0003

Data Index: 905296 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1345399 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0518. Min Act: -0.0003

Data Index: 399147 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1016799 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0439. Min Act: -0.0003

Data Index: 19841 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0451. Min Act: -0.0003

Data Index: 860141 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0490. Min Act: -0.0003

Data Index: 687785 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0452. Min Act: -0.0003

Data Index: 657772 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1138437 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0431. Min Act: -0.0003

Data Index: 410162 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0489. Min Act: -0.0003

Data Index: 361346 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0470. Min Act: -0.0003

Data Index: 80300 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1352880 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1058796 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1112159 (C4 (Web Text))

Max Activating Token Index: 778