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

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

Neuron 3251 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.2009. Min Act: -0.0001

Data Index: 454736 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.2030. Min Act: -0.0001

Data Index: 770226 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1810. Min Act: -0.0001

Data Index: 196848 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.2014. Min Act: -0.0000

Data Index: 466957 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1641. Min Act: -0.0001

Data Index: 1369623 (Python Code)

Max Activating Token Index: 301

Text #5

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1669. Min Act: -0.0001

Data Index: 845469 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1652. Min Act: -0.0001

Data Index: 231193 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1649. Min Act: -0.0001

Data Index: 790735 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1592. Min Act: -0.0000

Data Index: 673014 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1464. Min Act: -0.0000

Data Index: 978307 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1508. Min Act: -0.0001

Data Index: 134540 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1561. Min Act: -0.0001

Data Index: 306080 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1627. Min Act: -0.0001

Data Index: 637910 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1562. Min Act: -0.0000

Data Index: 710299 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1608. Min Act: -0.0000

Data Index: 926615 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1114410 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1087307 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1587. Min Act: -0.0001

Data Index: 52645 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1540. Min Act: -0.0001

Data Index: 550044 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.2030. Min Range: -0.2030

Max Act: 0.1698. Min Act: -0.0000

Data Index: 182680 (C4 (Web Text))

Max Activating Token Index: 551