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

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

Neuron 1096 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0001

Data Index: 141091 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1231124 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0985. Min Act: -0.0001

Data Index: 615277 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1093142 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0882. Min Act: -0.0001

Data Index: 854165 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0897. Min Act: -0.0001

Data Index: 639686 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0890. Min Act: -0.0001

Data Index: 43745 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0829. Min Act: -0.0001

Data Index: 39619 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1183211 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0763. Min Act: -0.0001

Data Index: 77721 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0763. Min Act: -0.0001

Data Index: 321122 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1185411 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1100463 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0734. Min Act: -0.0001

Data Index: 469066 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0760. Min Act: -0.0001

Data Index: 24951 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0787. Min Act: -0.0001

Data Index: 910554 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0818. Min Act: -0.0001

Data Index: 424683 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1040686 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0735. Min Act: -0.0001

Data Index: 749878 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0719. Min Act: -0.0001

Data Index: 118009 (C4 (Web Text))

Max Activating Token Index: 731