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

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

Neuron 201 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2275. Min Act: -0.0000

Data Index: 495265 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2328. Min Act: -0.0000

Data Index: 264595 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2219. Min Act: -0.0000

Data Index: 828840 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2320. Min Act: -0.0000

Data Index: 120900 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2108. Min Act: -0.0000

Data Index: 551444 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1517841 (Python Code)

Max Activating Token Index: 819

Text #6

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1956. Min Act: -0.0000

Data Index: 1018048 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1465849 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1993. Min Act: -0.0000

Data Index: 970637 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1898. Min Act: -0.0000

Data Index: 704272 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1878. Min Act: -0.0000

Data Index: 440382 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1395797 (Python Code)

Max Activating Token Index: 255

Text #12

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1487360 (Python Code)

Max Activating Token Index: 1012

Text #13

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1603955 (Python Code)

Max Activating Token Index: 984

Text #14

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1583905 (Python Code)

Max Activating Token Index: 957

Text #15

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1363232 (Python Code)

Max Activating Token Index: 970

Text #16

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1637. Min Act: -0.0000

Data Index: 266776 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1453218 (Python Code)

Max Activating Token Index: 979

Text #18

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1706. Min Act: -0.0000

Data Index: 226702 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.2328. Min Range: -0.2328

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1476756 (Python Code)

Max Activating Token Index: 1016