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

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

Neuron 3288 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.5799. Min Act: -0.0002

Data Index: 1109444 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.6237. Min Act: -0.0002

Data Index: 323500 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.5383. Min Act: -0.0002

Data Index: 457081 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.5447. Min Act: -0.0002

Data Index: 1236648 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.5115. Min Act: -0.0002

Data Index: 757123 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4799. Min Act: -0.0002

Data Index: 59139 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4758. Min Act: -0.0002

Data Index: 1150379 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4856. Min Act: -0.0002

Data Index: 724543 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4985. Min Act: -0.0002

Data Index: 339858 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.5027. Min Act: -0.0002

Data Index: 342673 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4497. Min Act: -0.0002

Data Index: 108223 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4527. Min Act: -0.0002

Data Index: 1246444 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4733. Min Act: -0.0002

Data Index: 656337 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4310. Min Act: -0.0002

Data Index: 544173 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4452. Min Act: -0.0002

Data Index: 1124127 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4438. Min Act: -0.0002

Data Index: 487523 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4107. Min Act: -0.0002

Data Index: 112527 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4006. Min Act: -0.0002

Data Index: 181369 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4148. Min Act: -0.0002

Data Index: 608404 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4318. Min Act: -0.0002

Data Index: 73235 (C4 (Web Text))

Max Activating Token Index: 180