Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6035 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0000

Data Index: 137796 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1145291 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1570468 (Python Code)

Max Activating Token Index: 567

Text #3

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0710. Min Act: -0.0000

Data Index: 239104 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1625676 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1636849 (Python Code)

Max Activating Token Index: 224

Text #6

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0661. Min Act: -0.0000

Data Index: 247558 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1611629 (Python Code)

Max Activating Token Index: 958

Text #8

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0633. Min Act: -0.0000

Data Index: 240865 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1485276 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1404753 (Python Code)

Max Activating Token Index: 1019

Text #11

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1638588 (Python Code)

Max Activating Token Index: 960

Text #12

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1443459 (Python Code)

Max Activating Token Index: 877

Text #13

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1459635 (Python Code)

Max Activating Token Index: 838

Text #14

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1287856 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1558476 (Python Code)

Max Activating Token Index: 434

Text #16

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0670. Min Act: -0.0000

Data Index: 1377381 (Python Code)

Max Activating Token Index: 415

Text #17

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0599. Min Act: -0.0000

Data Index: 565753 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0639. Min Act: -0.0000

Data Index: 995213 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0601. Min Act: -0.0000

Data Index: 940553 (C4 (Web Text))

Max Activating Token Index: 91