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

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

Neuron 439 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.2032. Min Act: -0.0005

Data Index: 349896 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.2139. Min Act: -0.0005

Data Index: 334242 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1952. Min Act: -0.0005

Data Index: 843747 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1912. Min Act: -0.0005

Data Index: 545555 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1956. Min Act: -0.0005

Data Index: 226497 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.2008. Min Act: -0.0005

Data Index: 982295 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1859. Min Act: -0.0005

Data Index: 706189 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1976. Min Act: -0.0005

Data Index: 517372 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1951. Min Act: -0.0004

Data Index: 680895 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1842. Min Act: -0.0005

Data Index: 122649 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1839. Min Act: -0.0005

Data Index: 465698 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1647. Min Act: -0.0005

Data Index: 158393 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1822. Min Act: -0.0005

Data Index: 1028950 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1744. Min Act: -0.0005

Data Index: 358933 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1746. Min Act: -0.0005

Data Index: 868061 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1795. Min Act: -0.0005

Data Index: 611331 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1808. Min Act: -0.0005

Data Index: 1152218 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1796. Min Act: -0.0005

Data Index: 904517 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1652. Min Act: -0.0005

Data Index: 484393 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.2139. Min Range: -0.2139

Max Act: 0.1781. Min Act: -0.0005

Data Index: 1181291 (C4 (Web Text))

Max Activating Token Index: 584