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

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

Neuron 3254 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: 0.2452. Min Range: -0.2452

Max Act: 0.2194. Min Act: 0.0000

Data Index: 1350042 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2452. Min Act: -0.0000

Data Index: 738225 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1203221 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1033467 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2101. Min Act: 0.0000

Data Index: 1189646 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.2020. Min Act: -0.0000

Data Index: 253835 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1913. Min Act: -0.0000

Data Index: 639103 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1937. Min Act: -0.0000

Data Index: 701169 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1992. Min Act: -0.0000

Data Index: 126413 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1826. Min Act: -0.0000

Data Index: 591946 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1811. Min Act: -0.0000

Data Index: 31383 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1838. Min Act: 0.0000

Data Index: 636519 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1691. Min Act: -0.0000

Data Index: 869097 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1645. Min Act: -0.0000

Data Index: 435663 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1697. Min Act: 0.0000

Data Index: 678512 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1630. Min Act: -0.0000

Data Index: 648275 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1790. Min Act: -0.0000

Data Index: 512050 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1648. Min Act: -0.0000

Data Index: 659982 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1646. Min Act: -0.0000

Data Index: 704831 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.2452. Min Range: -0.2452

Max Act: 0.1597. Min Act: -0.0000

Data Index: 56483 (C4 (Web Text))

Max Activating Token Index: 361