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

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

Neuron 780 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0691. Min Range: -1.0691

Max Act: 1.0416. Min Act: -0.0000

Data Index: 774646 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 1.0691. Min Range: -1.0691

Max Act: 1.0691. Min Act: -0.0000

Data Index: 891463 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.7550. Min Act: -0.0000

Data Index: 945723 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1163604 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.7155. Min Act: -0.0000

Data Index: 28711 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.7510. Min Act: -0.0000

Data Index: 889108 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.7046. Min Act: -0.0000

Data Index: 493585 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.6797. Min Act: -0.0000

Data Index: 181270 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.6852. Min Act: -0.0000

Data Index: 208411 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.5978. Min Act: -0.0000

Data Index: 949108 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.6006. Min Act: -0.0000

Data Index: 366746 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.5546. Min Act: -0.0000

Data Index: 405788 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.5883. Min Act: -0.0000

Data Index: 172164 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.6028. Min Act: -0.0000

Data Index: 163034 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1081167 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.5533. Min Act: -0.0000

Data Index: 704741 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.5684. Min Act: -0.0000

Data Index: 400838 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1291462 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.5854. Min Act: -0.0000

Data Index: 729007 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 1.0691. Min Range: -1.0691

Max Act: 0.5213. Min Act: -0.0000

Data Index: 249013 (C4 (Web Text))

Max Activating Token Index: 798