Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0720. Min Act: -0.0003

Data Index: 913361 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0782. Min Act: -0.0003

Data Index: 321068 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0760. Min Act: -0.0003

Data Index: 1254048 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0724. Min Act: -0.0003

Data Index: 102963 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0762. Min Act: -0.0003

Data Index: 661088 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1296011 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0651. Min Act: -0.0003

Data Index: 826119 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0822. Min Act: -0.0003

Data Index: 442846 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0694. Min Act: -0.0003

Data Index: 468388 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0674. Min Act: -0.0003

Data Index: 309303 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1100871 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1196032 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0611. Min Act: -0.0003

Data Index: 253977 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1357100 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0655. Min Act: -0.0003

Data Index: 510669 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0549. Min Act: -0.0003

Data Index: 441237 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0717. Min Act: -0.0003

Data Index: 1153605 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1297883 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0644. Min Act: -0.0003

Data Index: 827095 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1088491 (C4 (Web Text))

Max Activating Token Index: 300