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

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

Neuron 2837 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: 0.7032. Min Range: -0.7032

Max Act: 0.7032. Min Act: -0.0000

Data Index: 728255 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.6373. Min Act: -0.0000

Data Index: 507644 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5918. Min Act: -0.0000

Data Index: 585621 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5999. Min Act: -0.0000

Data Index: 393957 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5937. Min Act: -0.0000

Data Index: 177765 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5512. Min Act: 0.0000

Data Index: 1227151 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5518. Min Act: -0.0000

Data Index: 505129 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5368. Min Act: -0.0000

Data Index: 4276 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5675. Min Act: -0.0000

Data Index: 886676 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5523. Min Act: -0.0000

Data Index: 103966 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5496. Min Act: 0.0000

Data Index: 483206 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5863. Min Act: 0.0000

Data Index: 273332 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5260. Min Act: -0.0000

Data Index: 732473 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5422. Min Act: -0.0000

Data Index: 187575 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1354784 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5264. Min Act: -0.0000

Data Index: 470064 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5355. Min Act: 0.0000

Data Index: 1332081 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5191. Min Act: -0.0000

Data Index: 627120 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.5055. Min Act: -0.0000

Data Index: 878967 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.7032. Min Range: -0.7032

Max Act: 0.4988. Min Act: -0.0000

Data Index: 288068 (C4 (Web Text))

Max Activating Token Index: 74