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

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

Neuron 757 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: 0.0825. Min Range: -0.0825

Max Act: 0.0757. Min Act: -0.0003

Data Index: 182012 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0825. Min Act: -0.0003

Data Index: 1193352 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0818. Min Act: -0.0003

Data Index: 404015 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0748. Min Act: -0.0003

Data Index: 1338781 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0733. Min Act: -0.0003

Data Index: 936434 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0768. Min Act: -0.0003

Data Index: 671586 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0738. Min Act: -0.0003

Data Index: 865207 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0620. Min Act: -0.0003

Data Index: 707231 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0787. Min Act: -0.0003

Data Index: 36803 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0708. Min Act: -0.0003

Data Index: 69719 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0699. Min Act: -0.0003

Data Index: 178027 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0709. Min Act: -0.0003

Data Index: 134762 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0738. Min Act: -0.0003

Data Index: 1069303 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1282905 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0711. Min Act: -0.0003

Data Index: 1268693 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0694. Min Act: -0.0003

Data Index: 957572 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0665. Min Act: -0.0003

Data Index: 556363 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0709. Min Act: -0.0003

Data Index: 534518 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0657. Min Act: -0.0003

Data Index: 1020587 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0653. Min Act: -0.0003

Data Index: 585252 (C4 (Web Text))

Max Activating Token Index: 139