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

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

Neuron 83 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7976. Min Act: -0.0000

Data Index: 323300 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1223959 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1202020 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7701. Min Act: -0.0000

Data Index: 682918 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7123. Min Act: -0.0000

Data Index: 964499 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7066. Min Act: -0.0000

Data Index: 720898 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7300. Min Act: -0.0000

Data Index: 810280 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6944. Min Act: -0.0000

Data Index: 654272 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7205. Min Act: -0.0000

Data Index: 465093 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7053. Min Act: -0.0000

Data Index: 123235 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6817. Min Act: -0.0000

Data Index: 759958 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1101888 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6705. Min Act: -0.0000

Data Index: 931026 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6743. Min Act: -0.0000

Data Index: 1088981 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6489. Min Act: -0.0000

Data Index: 973599 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6652. Min Act: -0.0000

Data Index: 661965 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6678. Min Act: -0.0000

Data Index: 144801 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6610. Min Act: -0.0000

Data Index: 34429 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6791. Min Act: -0.0000

Data Index: 364781 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.7976. Min Range: -0.7976

Max Act: 0.6357. Min Act: -0.0000

Data Index: 637305 (C4 (Web Text))

Max Activating Token Index: 770