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

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

Neuron 3747 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5677. Min Act: -0.0000

Data Index: 761603 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3318. Min Act: -0.0000

Data Index: 258906 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1159344 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.2762. Min Act: -0.0000

Data Index: 328382 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.2460. Min Act: -0.0000

Data Index: 780129 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.2600. Min Act: -0.0000

Data Index: 154127 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.2849. Min Act: -0.0000

Data Index: 723891 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.2568. Min Act: -0.0000

Data Index: 771296 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.2422. Min Act: -0.0000

Data Index: 696163 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1012850 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.2252. Min Act: -0.0000

Data Index: 31683 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.2046. Min Act: -0.0000

Data Index: 601091 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.1641. Min Act: -0.0000

Data Index: 319573 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1294153 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1093633 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.1767. Min Act: -0.0000

Data Index: 575511 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.1645. Min Act: -0.0000

Data Index: 515424 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1213480 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.1561. Min Act: -0.0000

Data Index: 295690 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.1553. Min Act: -0.0000

Data Index: 59059 (C4 (Web Text))

Max Activating Token Index: 271