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

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

Neuron 6044 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: 0.2442. Min Range: -0.2442

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1032538 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.2003. Min Act: -0.0000

Data Index: 904943 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1426564 (Python Code)

Max Activating Token Index: 886

Text #3

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1782. Min Act: -0.0000

Data Index: 944292 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1008646 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1484888 (Python Code)

Max Activating Token Index: 518

Text #6

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.2089. Min Act: -0.0000

Data Index: 342597 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1895. Min Act: -0.0000

Data Index: 769946 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1904. Min Act: -0.0000

Data Index: 802366 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1214363 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1917. Min Act: -0.0000

Data Index: 345978 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1302523 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1201275 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1026514 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1695. Min Act: -0.0000

Data Index: 616410 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1898. Min Act: -0.0000

Data Index: 371478 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1761. Min Act: -0.0000

Data Index: 346840 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1910. Min Act: -0.0000

Data Index: 147771 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1225450 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.2442. Min Range: -0.2442

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1277533 (C4 (Web Text))

Max Activating Token Index: 220