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

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

Neuron 656 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2931. Min Act: -0.0001

Data Index: 721182 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3347. Min Act: -0.0001

Data Index: 1091211 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3122. Min Act: -0.0001

Data Index: 1185649 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2938. Min Act: -0.0001

Data Index: 1208581 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3226. Min Act: -0.0001

Data Index: 735962 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2959. Min Act: -0.0001

Data Index: 28696 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2852. Min Act: -0.0001

Data Index: 627684 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2763. Min Act: -0.0001

Data Index: 666662 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2943. Min Act: -0.0001

Data Index: 1340662 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2924. Min Act: -0.0001

Data Index: 1345747 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2975. Min Act: -0.0001

Data Index: 567820 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2824. Min Act: -0.0001

Data Index: 111292 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2534. Min Act: -0.0001

Data Index: 587077 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2622. Min Act: -0.0001

Data Index: 957280 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2646. Min Act: -0.0001

Data Index: 1153735 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2636. Min Act: -0.0001

Data Index: 1087835 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2632. Min Act: -0.0001

Data Index: 591521 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2712. Min Act: -0.0001

Data Index: 385075 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2614. Min Act: -0.0001

Data Index: 749272 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2766. Min Act: -0.0001

Data Index: 873764 (C4 (Web Text))

Max Activating Token Index: 414