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

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

Neuron 403 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: 5.7908. Min Range: -5.7908

Max Act: 5.3034. Min Act: -0.0001

Data Index: 49304 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.7908. Min Act: -0.0001

Data Index: 490009 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.2688. Min Act: -0.0001

Data Index: 785595 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.3701. Min Act: -0.0001

Data Index: 1244031 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.3845. Min Act: -0.0001

Data Index: 1002128 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.0005. Min Act: -0.0001

Data Index: 1143727 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.1423. Min Act: -0.0001

Data Index: 136520 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.0125. Min Act: -0.0001

Data Index: 673456 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.1590. Min Act: -0.0001

Data Index: 20158 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 5.7908. Min Range: -5.7908

Max Act: 4.9573. Min Act: -0.0001

Data Index: 924493 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.1126. Min Act: -0.0001

Data Index: 850251 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.0687. Min Act: -0.0001

Data Index: 930482 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 5.7908. Min Range: -5.7908

Max Act: 4.8970. Min Act: -0.0001

Data Index: 1190615 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 5.7908. Min Range: -5.7908

Max Act: 4.9089. Min Act: -0.0001

Data Index: 1100858 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.0562. Min Act: -0.0001

Data Index: 478796 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 5.7908. Min Range: -5.7908

Max Act: 4.6521. Min Act: -0.0001

Data Index: 744561 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 5.7908. Min Range: -5.7908

Max Act: 4.9981. Min Act: -0.0001

Data Index: 1114666 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 5.7908. Min Range: -5.7908

Max Act: 4.4926. Min Act: -0.0001

Data Index: 410894 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 5.7908. Min Range: -5.7908

Max Act: 5.0984. Min Act: -0.0001

Data Index: 702421 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 5.7908. Min Range: -5.7908

Max Act: 4.7846. Min Act: -0.0001

Data Index: 713102 (C4 (Web Text))

Max Activating Token Index: 268