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

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

Neuron 975 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: 0.2734. Min Range: -0.2734

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1205347 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2537. Min Act: -0.0000

Data Index: 70341 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2477. Min Act: -0.0000

Data Index: 834960 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2575. Min Act: -0.0000

Data Index: 446666 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2299. Min Act: -0.0000

Data Index: 904658 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1508518 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1370562 (Python Code)

Max Activating Token Index: 233

Text #7

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.2038. Min Act: -0.0000

Data Index: 333122 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1469. Min Act: -0.0000

Data Index: 114824 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1586. Min Act: -0.0000

Data Index: 734834 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1454. Min Act: -0.0000

Data Index: 660781 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1549. Min Act: -0.0000

Data Index: 243249 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1591. Min Act: -0.0000

Data Index: 439 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1516. Min Act: -0.0000

Data Index: 239730 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1533. Min Act: -0.0000

Data Index: 654175 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1396. Min Act: -0.0000

Data Index: 21632 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1320. Min Act: -0.0000

Data Index: 568993 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1343. Min Act: -0.0000

Data Index: 356621 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1107669 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.2734. Min Range: -0.2734

Max Act: 0.1445. Min Act: -0.0000

Data Index: 138380 (C4 (Web Text))

Max Activating Token Index: 849