Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3266 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.2369. Min Act: -0.0001

Data Index: 653016 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.2164. Min Act: -0.0001

Data Index: 746998 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.2019. Min Act: -0.0001

Data Index: 1640870 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.2137. Min Act: -0.0001

Data Index: 443371 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1891. Min Act: -0.0001

Data Index: 822217 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1804. Min Act: -0.0001

Data Index: 625810 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1837. Min Act: -0.0001

Data Index: 45557 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1054717 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1762. Min Act: -0.0001

Data Index: 121694 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1640. Min Act: -0.0001

Data Index: 749472 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1015141 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1537. Min Act: -0.0001

Data Index: 292836 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1584. Min Act: -0.0001

Data Index: 975135 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1618. Min Act: -0.0001

Data Index: 359746 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1551. Min Act: -0.0001

Data Index: 678253 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1029890 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1541. Min Act: -0.0001

Data Index: 77714 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1467. Min Act: -0.0001

Data Index: 520598 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1393. Min Act: -0.0001

Data Index: 419837 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.2369. Min Range: -0.2369

Max Act: 0.1391. Min Act: -0.0001

Data Index: 321027 (C4 (Web Text))

Max Activating Token Index: 976