Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2876 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9882. Min Act: -0.0001

Data Index: 839450 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9237. Min Act: -0.0001

Data Index: 402907 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8887. Min Act: -0.0001

Data Index: 587957 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8757. Min Act: -0.0001

Data Index: 1121726 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.9331. Min Act: -0.0001

Data Index: 15779 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8300. Min Act: -0.0001

Data Index: 813530 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8696. Min Act: -0.0001

Data Index: 218018 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8576. Min Act: -0.0001

Data Index: 496617 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7840. Min Act: -0.0001

Data Index: 1269121 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7118. Min Act: -0.0001

Data Index: 1101044 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7517. Min Act: -0.0001

Data Index: 135274 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.8060. Min Act: -0.0001

Data Index: 876569 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7418. Min Act: -0.0001

Data Index: 607548 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7364. Min Act: -0.0001

Data Index: 681501 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7868. Min Act: -0.0001

Data Index: 1196539 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.6766. Min Act: -0.0001

Data Index: 419159 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.6837. Min Act: -0.0001

Data Index: 731462 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.6690. Min Act: -0.0001

Data Index: 1232499 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.6639. Min Act: -0.0001

Data Index: 1179005 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.9882. Min Range: -0.9882

Max Act: 0.7083. Min Act: -0.0001

Data Index: 914040 (C4 (Web Text))

Max Activating Token Index: 412