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

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

Neuron 4924 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0753. Min Act: -0.0002

Data Index: 83668 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1353564 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0719. Min Act: -0.0002

Data Index: 145867 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1048511 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0693. Min Act: -0.0002

Data Index: 703172 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1278030 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0662. Min Act: -0.0002

Data Index: 564848 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1091038 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0675. Min Act: -0.0002

Data Index: 438634 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1288538 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0658. Min Act: -0.0002

Data Index: 587911 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0624. Min Act: -0.0002

Data Index: 976652 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0643. Min Act: -0.0002

Data Index: 357695 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1013666 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1242564 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0628. Min Act: -0.0002

Data Index: 262582 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1075947 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0603. Min Act: -0.0002

Data Index: 232805 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0603. Min Act: -0.0002

Data Index: 51022 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0611. Min Act: -0.0002

Data Index: 924444 (C4 (Web Text))

Max Activating Token Index: 398