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

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

Neuron 4043 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.1211. Min Act: -0.0002

Data Index: 867531 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.2478. Min Act: -0.0001

Data Index: 933842 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.0840. Min Act: -0.0002

Data Index: 941951 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.2857. Min Act: -0.0002

Data Index: 103958 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.2918. Min Act: -0.0002

Data Index: 804604 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.1912. Min Act: -0.0001

Data Index: 586611 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.1715. Min Act: -0.0001

Data Index: 987236 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.1458. Min Act: -0.0001

Data Index: 635605 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.2146. Min Act: -0.0002

Data Index: 550693 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.0811. Min Act: -0.0001

Data Index: 295695 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.2187. Min Act: -0.0001

Data Index: 435254 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.2160. Min Act: -0.0001

Data Index: 521571 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.0620. Min Act: -0.0001

Data Index: 1270347 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.1291. Min Act: -0.0001

Data Index: 445728 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.1199. Min Act: -0.0001

Data Index: 1450844 (Python Code)

Max Activating Token Index: 303

Text #15

Max Range: 1.2918. Min Range: -1.2918

Max Act: 0.9546. Min Act: -0.0002

Data Index: 1062109 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.1009. Min Act: -0.0001

Data Index: 983252 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.0013. Min Act: -0.0001

Data Index: 740092 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.0961. Min Act: -0.0001

Data Index: 1144278 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 1.2918. Min Range: -1.2918

Max Act: 1.0126. Min Act: -0.0001

Data Index: 966513 (C4 (Web Text))

Max Activating Token Index: 79