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

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

Neuron 3890 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0666. Min Act: -0.0002

Data Index: 189608 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0697. Min Act: -0.0002

Data Index: 544851 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1091917 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0618. Min Act: -0.0002

Data Index: 128904 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0643. Min Act: -0.0002

Data Index: 58063 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0649. Min Act: -0.0002

Data Index: 459747 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0609. Min Act: -0.0002

Data Index: 818522 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0676. Min Act: -0.0002

Data Index: 45813 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1252373 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0604. Min Act: -0.0002

Data Index: 779704 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0600. Min Act: -0.0002

Data Index: 62002 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0594. Min Act: -0.0002

Data Index: 809491 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1097109 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0539. Min Act: -0.0002

Data Index: 551959 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0576. Min Act: -0.0002

Data Index: 192149 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0564. Min Act: -0.0002

Data Index: 453725 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1333932 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0560. Min Act: -0.0002

Data Index: 67096 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0532. Min Act: -0.0002

Data Index: 673679 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.0697. Min Range: -0.0697

Max Act: 0.0570. Min Act: -0.0002

Data Index: 165031 (C4 (Web Text))

Max Activating Token Index: 17