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

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

Neuron 1647 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2362. Min Act: -0.0000

Data Index: 896539 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2287. Min Act: -0.0000

Data Index: 358662 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2181. Min Act: -0.0001

Data Index: 199840 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2192. Min Act: -0.0000

Data Index: 81179 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2028. Min Act: 0.0000

Data Index: 1129919 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2067. Min Act: -0.0001

Data Index: 919632 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2111. Min Act: -0.0000

Data Index: 247349 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2068. Min Act: 0.0001

Data Index: 1062275 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2015. Min Act: -0.0000

Data Index: 27494 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1200389 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1247472 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1802. Min Act: -0.0001

Data Index: 796654 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1879. Min Act: -0.0000

Data Index: 152721 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1937. Min Act: 0.0000

Data Index: 804986 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.2081. Min Act: -0.0001

Data Index: 603923 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1855. Min Act: 0.0000

Data Index: 1031125 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1825. Min Act: -0.0000

Data Index: 738215 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1864. Min Act: -0.0001

Data Index: 550599 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1862. Min Act: -0.0001

Data Index: 882202 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.2362. Min Range: -0.2362

Max Act: 0.1875. Min Act: -0.0001

Data Index: 293109 (C4 (Web Text))

Max Activating Token Index: 661