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

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

Neuron 3009 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9241. Min Act: -0.0000

Data Index: 1004515 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9531. Min Act: -0.0000

Data Index: 1183541 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9031. Min Act: -0.0000

Data Index: 912684 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9397. Min Act: -0.0000

Data Index: 82655 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8675. Min Act: -0.0000

Data Index: 458242 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9006. Min Act: -0.0000

Data Index: 467740 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8766. Min Act: -0.0000

Data Index: 122623 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7736. Min Act: -0.0000

Data Index: 1252767 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1035718 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7789. Min Act: -0.0000

Data Index: 692893 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7760. Min Act: -0.0000

Data Index: 495851 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7436. Min Act: -0.0000

Data Index: 194915 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7593. Min Act: -0.0000

Data Index: 272387 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7594. Min Act: -0.0000

Data Index: 849979 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1124240 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1097062 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7237. Min Act: -0.0000

Data Index: 190186 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7316. Min Act: -0.0000

Data Index: 973931 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7284. Min Act: -0.0000

Data Index: 788359 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7256. Min Act: -0.0000

Data Index: 464331 (C4 (Web Text))

Max Activating Token Index: 551