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

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

Neuron 3700 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1553. Min Act: -0.0001

Data Index: 657789 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1432. Min Act: -0.0001

Data Index: 18004 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1208. Min Act: -0.0001

Data Index: 571773 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1112. Min Act: -0.0001

Data Index: 695842 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1041. Min Act: -0.0001

Data Index: 577518 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0944. Min Act: -0.0001

Data Index: 299525 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.1004. Min Act: -0.0001

Data Index: 704671 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1295708 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1590 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1200282 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0946. Min Act: -0.0001

Data Index: 831938 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0781. Min Act: -0.0001

Data Index: 229473 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1272286 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0853. Min Act: -0.0001

Data Index: 622578 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0851. Min Act: -0.0001

Data Index: 349064 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1188401 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0858. Min Act: -0.0001

Data Index: 803659 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0766. Min Act: -0.0001

Data Index: 1358531 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1301327 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.1553. Min Range: -0.1553

Max Act: 0.0789. Min Act: -0.0001

Data Index: 1093199 (C4 (Web Text))

Max Activating Token Index: 110