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

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

Neuron 2707 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3767. Min Act: -0.0000

Data Index: 78823 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.5229. Min Act: -0.0000

Data Index: 383605 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2815. Min Act: -0.0000

Data Index: 908813 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.5989. Min Act: -0.0000

Data Index: 507430 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.4046. Min Act: -0.0001

Data Index: 1078300 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3046. Min Act: -0.0000

Data Index: 732889 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.4240. Min Act: -0.0000

Data Index: 767997 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3659. Min Act: -0.0000

Data Index: 652990 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1120688 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2726. Min Act: -0.0000

Data Index: 1292326 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.4335. Min Act: -0.0000

Data Index: 1045762 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2763. Min Act: -0.0000

Data Index: 453882 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2090. Min Act: -0.0000

Data Index: 729566 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1244522 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.1962. Min Act: -0.0000

Data Index: 972868 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.1408. Min Act: -0.0000

Data Index: 855046 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.0550. Min Act: -0.0001

Data Index: 1215496 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2045. Min Act: -0.0000

Data Index: 86475 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.1642. Min Act: -0.0000

Data Index: 580241 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.0991. Min Act: -0.0000

Data Index: 1292869 (C4 (Web Text))

Max Activating Token Index: 177