Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 562 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2797. Min Act: -0.0001

Data Index: 134226 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2370. Min Act: -0.0001

Data Index: 608965 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2398. Min Act: -0.0001

Data Index: 1088205 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2390. Min Act: -0.0001

Data Index: 342290 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1306942 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2460. Min Act: -0.0001

Data Index: 447432 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2263. Min Act: -0.0001

Data Index: 72222 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2412. Min Act: -0.0001

Data Index: 892623 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2147. Min Act: -0.0001

Data Index: 980618 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1852. Min Act: -0.0001

Data Index: 11058 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2172. Min Act: -0.0001

Data Index: 750663 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1899. Min Act: -0.0001

Data Index: 716450 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1827. Min Act: -0.0001

Data Index: 117273 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1837. Min Act: -0.0001

Data Index: 511079 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1778. Min Act: -0.0001

Data Index: 582937 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1151828 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1776. Min Act: -0.0001

Data Index: 700062 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1704. Min Act: -0.0001

Data Index: 770885 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1690. Min Act: -0.0001

Data Index: 842694 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1821. Min Act: -0.0001

Data Index: 85507 (C4 (Web Text))

Max Activating Token Index: 574