Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 708 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.3159. Min Act: -0.0000

Data Index: 145151 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1040844 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.3366. Min Act: -0.0000

Data Index: 206670 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.3149. Min Act: -0.0001

Data Index: 484354 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.3192. Min Act: -0.0000

Data Index: 901654 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.2871. Min Act: -0.0000

Data Index: 182334 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.2464. Min Act: -0.0000

Data Index: 888006 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.2872. Min Act: -0.0000

Data Index: 491231 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.3179. Min Act: -0.0000

Data Index: 15740 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1217520 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.3078. Min Act: -0.0000

Data Index: 79982 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1252576 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.2661. Min Act: -0.0000

Data Index: 590506 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.2724. Min Act: -0.0000

Data Index: 542960 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.2706. Min Act: -0.0000

Data Index: 959786 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.2656. Min Act: -0.0000

Data Index: 512030 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.2931. Min Act: -0.0000

Data Index: 651125 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.2745. Min Act: -0.0000

Data Index: 846355 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.2703. Min Act: -0.0000

Data Index: 136606 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.3606. Min Range: -0.3606

Max Act: 0.2694. Min Act: -0.0000

Data Index: 801165 (C4 (Web Text))

Max Activating Token Index: 163