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

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

Neuron 2492 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: 1.0687. Min Range: -1.0687

Max Act: 1.0687. Min Act: -0.0002

Data Index: 976127 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.9606. Min Act: -0.0002

Data Index: 704269 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.9690. Min Act: -0.0002

Data Index: 254589 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 1.0687. Min Range: -1.0687

Max Act: 1.0115. Min Act: -0.0002

Data Index: 1233736 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.9713. Min Act: -0.0002

Data Index: 570715 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.8835. Min Act: -0.0002

Data Index: 971110 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.9913. Min Act: -0.0002

Data Index: 738796 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.9389. Min Act: -0.0002

Data Index: 678258 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.9162. Min Act: -0.0002

Data Index: 330993 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.9361. Min Act: -0.0002

Data Index: 88777 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.8742. Min Act: -0.0002

Data Index: 1142788 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.8987. Min Act: -0.0002

Data Index: 249063 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.8699. Min Act: -0.0002

Data Index: 1311751 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.9167. Min Act: -0.0002

Data Index: 627390 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.9059. Min Act: -0.0002

Data Index: 741911 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.8861. Min Act: -0.0002

Data Index: 87699 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.8999. Min Act: -0.0002

Data Index: 1143984 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.8667. Min Act: -0.0002

Data Index: 345352 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.8699. Min Act: -0.0002

Data Index: 880691 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 1.0687. Min Range: -1.0687

Max Act: 0.8509. Min Act: -0.0002

Data Index: 1286809 (C4 (Web Text))

Max Activating Token Index: 277