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

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

Neuron 2068 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.2137. Min Act: -0.0001

Data Index: 626383 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1903. Min Act: -0.0001

Data Index: 679067 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.2170. Min Act: -0.0001

Data Index: 85935 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.2105. Min Act: -0.0001

Data Index: 1038236 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.2103. Min Act: -0.0001

Data Index: 311325 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.2003. Min Act: -0.0001

Data Index: 301583 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.2064. Min Act: -0.0001

Data Index: 404723 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1800. Min Act: -0.0001

Data Index: 1219455 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1926. Min Act: -0.0001

Data Index: 207545 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1926. Min Act: -0.0001

Data Index: 498680 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1052540 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1828. Min Act: -0.0001

Data Index: 468929 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1925. Min Act: -0.0001

Data Index: 465501 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1897. Min Act: -0.0001

Data Index: 1228695 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1901. Min Act: -0.0001

Data Index: 41796 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1509. Min Act: -0.0001

Data Index: 945632 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1728. Min Act: -0.0001

Data Index: 1015529 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1080878 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1796. Min Act: -0.0001

Data Index: 457043 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.2170. Min Range: -0.2170

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1265266 (C4 (Web Text))

Max Activating Token Index: 625