Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2639 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2027. Min Act: -0.0001

Data Index: 610379 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2673. Min Act: -0.0001

Data Index: 984906 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2291. Min Act: -0.0001

Data Index: 556419 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2614. Min Act: -0.0001

Data Index: 504247 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2757. Min Act: -0.0001

Data Index: 760737 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2246. Min Act: -0.0001

Data Index: 567109 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2160. Min Act: -0.0001

Data Index: 356949 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2068. Min Act: -0.0001

Data Index: 1206674 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2347. Min Act: -0.0001

Data Index: 809122 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1902. Min Act: -0.0001

Data Index: 755960 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1996. Min Act: -0.0001

Data Index: 1267158 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2265. Min Act: -0.0001

Data Index: 51851 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2014. Min Act: -0.0001

Data Index: 436771 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2056. Min Act: -0.0001

Data Index: 1264286 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1982. Min Act: -0.0001

Data Index: 941657 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2038. Min Act: -0.0001

Data Index: 643617 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2194. Min Act: -0.0001

Data Index: 1155938 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2089. Min Act: -0.0001

Data Index: 1345731 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2139. Min Act: -0.0001

Data Index: 929600 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1996. Min Act: -0.0001

Data Index: 1180847 (C4 (Web Text))

Max Activating Token Index: 733