Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2241 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0747. Min Act: -0.0003

Data Index: 834118 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0681. Min Act: -0.0003

Data Index: 1305092 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0725. Min Act: -0.0003

Data Index: 786172 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0715. Min Act: -0.0003

Data Index: 1136850 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0730. Min Act: -0.0003

Data Index: 11261 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1517708 (Python Code)

Max Activating Token Index: 350

Text #6

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0666. Min Act: -0.0003

Data Index: 554222 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0670. Min Act: -0.0003

Data Index: 1601473 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0630. Min Act: -0.0003

Data Index: 361432 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0646. Min Act: -0.0003

Data Index: 223493 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1531584 (Python Code)

Max Activating Token Index: 828

Text #11

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1100216 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1407056 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0555. Min Act: -0.0003

Data Index: 843655 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0502. Min Act: -0.0003

Data Index: 263386 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0559. Min Act: -0.0003

Data Index: 604503 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1455823 (Python Code)

Max Activating Token Index: 640

Text #17

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0556. Min Act: -0.0004

Data Index: 639357 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0576. Min Act: -0.0003

Data Index: 844828 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0512. Min Act: -0.0003

Data Index: 693152 (C4 (Web Text))

Max Activating Token Index: 489