Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 931 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2279. Min Act: -0.0002

Data Index: 493974 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2163. Min Act: -0.0002

Data Index: 328388 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2103. Min Act: -0.0002

Data Index: 198370 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1926. Min Act: -0.0002

Data Index: 950397 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1924. Min Act: -0.0002

Data Index: 1209876 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1870. Min Act: -0.0002

Data Index: 1051985 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1957. Min Act: -0.0002

Data Index: 923813 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1831. Min Act: -0.0002

Data Index: 972714 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1877. Min Act: -0.0002

Data Index: 821218 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2001. Min Act: -0.0002

Data Index: 900552 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1885. Min Act: -0.0002

Data Index: 37654 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1784. Min Act: -0.0002

Data Index: 964061 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1815. Min Act: -0.0002

Data Index: 359315 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1845. Min Act: -0.0002

Data Index: 489399 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1847. Min Act: -0.0001

Data Index: 617717 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1630. Min Act: -0.0002

Data Index: 1159985 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1708. Min Act: -0.0002

Data Index: 1059683 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1747. Min Act: -0.0002

Data Index: 545444 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1756. Min Act: -0.0002

Data Index: 982693 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1827. Min Act: -0.0002

Data Index: 962484 (C4 (Web Text))

Max Activating Token Index: 915