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

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

Neuron 4946 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2948. Min Act: -0.0001

Data Index: 433160 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2472. Min Act: -0.0001

Data Index: 918317 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2103. Min Act: -0.0001

Data Index: 1337492 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2515. Min Act: -0.0001

Data Index: 677558 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1637498 (Python Code)

Max Activating Token Index: 618

Text #5

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2191. Min Act: -0.0001

Data Index: 322349 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2056. Min Act: -0.0001

Data Index: 797101 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2060. Min Act: -0.0001

Data Index: 656080 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2095. Min Act: -0.0001

Data Index: 1252040 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1009773 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1863. Min Act: -0.0001

Data Index: 989804 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2215. Min Act: -0.0001

Data Index: 848817 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1805. Min Act: -0.0001

Data Index: 1385738 (Python Code)

Max Activating Token Index: 992

Text #13

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1853. Min Act: -0.0001

Data Index: 891761 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1016042 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1402832 (Python Code)

Max Activating Token Index: 426

Text #16

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1689. Min Act: -0.0001

Data Index: 633875 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1736. Min Act: -0.0001

Data Index: 108134 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1643735 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1682. Min Act: -0.0001

Data Index: 648689 (C4 (Web Text))

Max Activating Token Index: 1018