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

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

Neuron 972 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: 0.9884. Min Range: -0.9884

Max Act: 0.9884. Min Act: -0.0001

Data Index: 1350338 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.9871. Min Act: -0.0001

Data Index: 631591 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.9121. Min Act: -0.0001

Data Index: 25936 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.9034. Min Act: -0.0001

Data Index: 920970 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.8722. Min Act: -0.0001

Data Index: 929616 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.9108. Min Act: -0.0001

Data Index: 1287078 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.8617. Min Act: -0.0001

Data Index: 130571 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.8327. Min Act: -0.0001

Data Index: 1093165 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.8561. Min Act: -0.0001

Data Index: 1349838 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.8688. Min Act: -0.0001

Data Index: 1231745 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.8350. Min Act: -0.0001

Data Index: 695020 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.8090. Min Act: -0.0001

Data Index: 684781 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.8119. Min Act: -0.0001

Data Index: 785375 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.7906. Min Act: -0.0001

Data Index: 927311 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.8331. Min Act: -0.0001

Data Index: 477352 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.7749. Min Act: -0.0001

Data Index: 463916 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.8163. Min Act: -0.0001

Data Index: 1023978 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.7664. Min Act: -0.0001

Data Index: 1185916 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.7615. Min Act: -0.0001

Data Index: 574795 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1343932 (C4 (Web Text))

Max Activating Token Index: 165