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

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

Neuron 3961 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7564. Min Range: -2.7564

Max Act: 2.7564. Min Act: -0.0000

Data Index: 570324 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 2.7564. Min Range: -2.7564

Max Act: 2.1918. Min Act: -0.0000

Data Index: 776257 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.9244. Min Act: -0.0000

Data Index: 44583 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 2.7564. Min Range: -2.7564

Max Act: 2.1108. Min Act: -0.0000

Data Index: 925951 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.9730. Min Act: -0.0000

Data Index: 1359767 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 2.7564. Min Range: -2.7564

Max Act: 2.1385. Min Act: -0.0000

Data Index: 732153 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 2.7564. Min Range: -2.7564

Max Act: 2.1866. Min Act: -0.0000

Data Index: 728075 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 2.7564. Min Range: -2.7564

Max Act: 2.3563. Min Act: -0.0000

Data Index: 698584 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.8719. Min Act: -0.0000

Data Index: 1314009 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 2.7564. Min Range: -2.7564

Max Act: 2.0297. Min Act: -0.0000

Data Index: 1012527 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.5999. Min Act: -0.0000

Data Index: 1004198 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.8798. Min Act: -0.0000

Data Index: 862486 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.7391. Min Act: -0.0000

Data Index: 845737 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.7128. Min Act: -0.0000

Data Index: 1260300 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.6772. Min Act: -0.0000

Data Index: 611938 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.8512. Min Act: -0.0000

Data Index: 311580 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.7365. Min Act: -0.0000

Data Index: 777999 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.7615. Min Act: -0.0000

Data Index: 809939 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.8875. Min Act: -0.0000

Data Index: 1348014 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 2.7564. Min Range: -2.7564

Max Act: 1.9212. Min Act: -0.0000

Data Index: 142681 (C4 (Web Text))

Max Activating Token Index: 494