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

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

Neuron 4719 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3556. Min Act: -0.0000

Data Index: 404112 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1146619 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3834. Min Act: -0.0000

Data Index: 804457 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.4050. Min Act: -0.0000

Data Index: 471230 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3757. Min Act: -0.0000

Data Index: 148790 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.2793. Min Act: -0.0000

Data Index: 671299 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.2421. Min Act: -0.0000

Data Index: 427973 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1328915 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.2192. Min Act: -0.0000

Data Index: 471804 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.1981. Min Act: -0.0000

Data Index: 805593 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.1835. Min Act: -0.0000

Data Index: 806722 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1104624 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1182487 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.1753. Min Act: -0.0000

Data Index: 418501 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1260740 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.1806. Min Act: -0.0000

Data Index: 385584 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.1739. Min Act: -0.0000

Data Index: 281872 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1149496 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.1649. Min Act: -0.0000

Data Index: 476339 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.1782. Min Act: -0.0000

Data Index: 137536 (C4 (Web Text))

Max Activating Token Index: 791