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

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

Neuron 3590 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1103355 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.9028. Min Act: -0.0000

Data Index: 250692 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.8259. Min Act: -0.0000

Data Index: 783805 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.8383. Min Act: -0.0000

Data Index: 995073 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1250149 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7709. Min Act: -0.0000

Data Index: 532730 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1253731 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1154802 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1348756 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7808. Min Act: -0.0000

Data Index: 700462 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7726. Min Act: -0.0000

Data Index: 644752 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7652. Min Act: -0.0000

Data Index: 552031 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7800. Min Act: -0.0000

Data Index: 574309 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7013. Min Act: -0.0000

Data Index: 704616 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1253364 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.6813. Min Act: -0.0000

Data Index: 680244 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.7203. Min Act: -0.0000

Data Index: 41819 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.6762. Min Act: -0.0000

Data Index: 791566 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.6929. Min Act: -0.0000

Data Index: 620080 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.9701. Min Range: -0.9701

Max Act: 0.6821. Min Act: -0.0000

Data Index: 346325 (C4 (Web Text))

Max Activating Token Index: 86