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

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

Neuron 529 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: 0.2249. Min Range: -0.2249

Max Act: 0.2249. Min Act: -0.0000

Data Index: 409879 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.2141. Min Act: -0.0000

Data Index: 525154 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1964. Min Act: -0.0000

Data Index: 864629 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.2156. Min Act: -0.0000

Data Index: 120498 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1834. Min Act: -0.0000

Data Index: 238444 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1795. Min Act: -0.0000

Data Index: 661664 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1853. Min Act: -0.0000

Data Index: 362079 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1861. Min Act: -0.0000

Data Index: 579377 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1725. Min Act: -0.0000

Data Index: 438707 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1717. Min Act: -0.0000

Data Index: 999353 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1731. Min Act: -0.0000

Data Index: 470926 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1304297 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1707. Min Act: -0.0000

Data Index: 506666 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1589701 (Python Code)

Max Activating Token Index: 1013

Text #14

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1851. Min Act: -0.0000

Data Index: 160987 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1051267 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1877. Min Act: -0.0000

Data Index: 557419 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1683. Min Act: -0.0000

Data Index: 856964 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1738. Min Act: -0.0000

Data Index: 419914 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1656. Min Act: -0.0000

Data Index: 761117 (C4 (Web Text))

Max Activating Token Index: 967