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

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

Neuron 1882 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.1243. Min Act: -0.0000

Data Index: 678172 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1366914 (Python Code)

Max Activating Token Index: 765

Text #2

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.2130. Min Act: -0.0000

Data Index: 944939 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1481375 (Python Code)

Max Activating Token Index: 97

Text #4

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0655. Min Act: -0.0000

Data Index: 490784 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0774. Min Act: -0.0000

Data Index: 182296 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0899. Min Act: -0.0000

Data Index: 1405443 (Python Code)

Max Activating Token Index: 378

Text #7

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.1168. Min Act: -0.0000

Data Index: 1402440 (Python Code)

Max Activating Token Index: 1012

Text #8

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0728. Min Act: -0.0000

Data Index: 1403668 (Python Code)

Max Activating Token Index: 719

Text #9

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1533471 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1426028 (Python Code)

Max Activating Token Index: 364

Text #11

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.9775. Min Act: -0.0000

Data Index: 32390 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1427488 (Python Code)

Max Activating Token Index: 453

Text #13

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0456. Min Act: -0.0000

Data Index: 660465 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.9707. Min Act: -0.0000

Data Index: 1557060 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 1.2130. Min Range: -1.2130

Max Act: 1.0772. Min Act: -0.0000

Data Index: 725207 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.9626. Min Act: -0.0000

Data Index: 1441583 (Python Code)

Max Activating Token Index: 243

Text #17

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.7782. Min Act: -0.0000

Data Index: 554355 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1541667 (Python Code)

Max Activating Token Index: 960

Text #19

Max Range: 1.2130. Min Range: -1.2130

Max Act: 0.9620. Min Act: -0.0000

Data Index: 1594723 (Python Code)

Max Activating Token Index: 103