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

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

Neuron 3622 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: 0.7492. Min Range: -0.7492

Max Act: 0.7492. Min Act: -0.0000

Data Index: 686697 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7113. Min Act: -0.0000

Data Index: 410162 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7100. Min Act: -0.0000

Data Index: 659948 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7082. Min Act: -0.0000

Data Index: 479398 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.7003. Min Act: -0.0000

Data Index: 381922 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6839. Min Act: -0.0000

Data Index: 672825 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6571. Min Act: -0.0000

Data Index: 328679 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6950. Min Act: -0.0000

Data Index: 759339 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6937. Min Act: -0.0000

Data Index: 168542 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6756. Min Act: -0.0000

Data Index: 161603 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6412. Min Act: -0.0000

Data Index: 374289 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6144. Min Act: -0.0000

Data Index: 710058 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6499. Min Act: -0.0000

Data Index: 956894 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6328. Min Act: -0.0000

Data Index: 330326 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1161798 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6119. Min Act: -0.0000

Data Index: 635795 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1219692 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6070. Min Act: -0.0000

Data Index: 846219 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1242166 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.7492. Min Range: -0.7492

Max Act: 0.5700. Min Act: -0.0000

Data Index: 423138 (C4 (Web Text))

Max Activating Token Index: 695