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

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

Neuron 846 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5959. Min Range: -1.5959

Max Act: 1.5959. Min Act: -0.0000

Data Index: 924279 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 1.5959. Min Range: -1.5959

Max Act: 1.5129. Min Act: -0.0000

Data Index: 124055 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 1.5959. Min Range: -1.5959

Max Act: 1.4468. Min Act: -0.0001

Data Index: 860791 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 1.5959. Min Range: -1.5959

Max Act: 1.3974. Min Act: -0.0001

Data Index: 1270052 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 1.5959. Min Range: -1.5959

Max Act: 1.2648. Min Act: -0.0000

Data Index: 948934 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 1.5959. Min Range: -1.5959

Max Act: 1.2672. Min Act: -0.0001

Data Index: 533871 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 1.5959. Min Range: -1.5959

Max Act: 1.2595. Min Act: -0.0000

Data Index: 595378 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.5959. Min Range: -1.5959

Max Act: 1.2573. Min Act: -0.0001

Data Index: 96455 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 1.5959. Min Range: -1.5959

Max Act: 1.0002. Min Act: -0.0000

Data Index: 723433 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 1.5959. Min Range: -1.5959

Max Act: 0.9491. Min Act: -0.0001

Data Index: 1093846 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 1.5959. Min Range: -1.5959

Max Act: 1.0010. Min Act: -0.0000

Data Index: 1136727 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 1.5959. Min Range: -1.5959

Max Act: 0.7809. Min Act: -0.0001

Data Index: 389781 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 1.5959. Min Range: -1.5959

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1013769 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 1.5959. Min Range: -1.5959

Max Act: 0.8227. Min Act: -0.0001

Data Index: 827867 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 1.5959. Min Range: -1.5959

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1273492 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 1.5959. Min Range: -1.5959

Max Act: 0.8584. Min Act: -0.0000

Data Index: 9976 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 1.5959. Min Range: -1.5959

Max Act: 0.7608. Min Act: -0.0001

Data Index: 1129614 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.5959. Min Range: -1.5959

Max Act: 0.8609. Min Act: -0.0000

Data Index: 463169 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 1.5959. Min Range: -1.5959

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1144153 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 1.5959. Min Range: -1.5959

Max Act: 0.8526. Min Act: -0.0000

Data Index: 457141 (C4 (Web Text))

Max Activating Token Index: 90