Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4444 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1708. Min Range: -2.1708

Max Act: 2.1563. Min Act: -0.0000

Data Index: 53152 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 2.1708. Min Range: -2.1708

Max Act: 2.1708. Min Act: -0.0000

Data Index: 1130760 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 2.1708. Min Range: -2.1708

Max Act: 2.1098. Min Act: -0.0000

Data Index: 1118853 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 2.1708. Min Range: -2.1708

Max Act: 2.0064. Min Act: -0.0000

Data Index: 285414 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 2.1708. Min Range: -2.1708

Max Act: 2.0775. Min Act: -0.0000

Data Index: 1306940 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 2.1708. Min Range: -2.1708

Max Act: 2.1538. Min Act: -0.0000

Data Index: 1259975 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.9074. Min Act: -0.0000

Data Index: 8458 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.9048. Min Act: -0.0000

Data Index: 1069160 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.7817. Min Act: -0.0000

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.8629. Min Act: -0.0000

Data Index: 879738 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.9163. Min Act: -0.0000

Data Index: 1173651 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.9129. Min Act: -0.0000

Data Index: 1234939 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 2.1708. Min Range: -2.1708

Max Act: 2.0083. Min Act: -0.0000

Data Index: 248455 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.9814. Min Act: -0.0000

Data Index: 602836 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.9911. Min Act: -0.0000

Data Index: 1779 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.8824. Min Act: -0.0000

Data Index: 15574 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.7656. Min Act: -0.0000

Data Index: 562873 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.8668. Min Act: -0.0000

Data Index: 442885 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.8398. Min Act: -0.0000

Data Index: 1268636 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 2.1708. Min Range: -2.1708

Max Act: 1.8366. Min Act: -0.0000

Data Index: 1112865 (C4 (Web Text))

Max Activating Token Index: 461