Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2395 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0848. Min Act: -0.0002

Data Index: 275813 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0796. Min Act: -0.0002

Data Index: 626867 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0704. Min Act: -0.0002

Data Index: 872616 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0700. Min Act: -0.0002

Data Index: 148845 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0691. Min Act: -0.0002

Data Index: 662243 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0658. Min Act: -0.0002

Data Index: 675535 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1331955 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0610. Min Act: -0.0002

Data Index: 236609 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0679. Min Act: -0.0002

Data Index: 867750 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0693. Min Act: -0.0002

Data Index: 368044 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0613. Min Act: -0.0002

Data Index: 113002 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1181711 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0613. Min Act: -0.0002

Data Index: 459296 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0637. Min Act: -0.0002

Data Index: 728524 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1344017 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0633. Min Act: -0.0002

Data Index: 857787 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1288839 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0601. Min Act: -0.0002

Data Index: 122451 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0592. Min Act: -0.0002

Data Index: 185433 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0615. Min Act: -0.0002

Data Index: 54600 (C4 (Web Text))

Max Activating Token Index: 881