Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 612 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0825. Min Act: -0.0005

Data Index: 188956 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0719. Min Act: -0.0005

Data Index: 832837 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0662. Min Act: -0.0005

Data Index: 75081 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0627. Min Act: -0.0005

Data Index: 833423 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0578. Min Act: -0.0005

Data Index: 203752 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0621. Min Act: -0.0005

Data Index: 964447 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0549. Min Act: -0.0005

Data Index: 63424 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0600. Min Act: -0.0005

Data Index: 728117 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0551. Min Act: -0.0005

Data Index: 445395 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0578. Min Act: -0.0005

Data Index: 445735 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0552. Min Act: -0.0005

Data Index: 352144 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0575. Min Act: -0.0005

Data Index: 1303832 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0565. Min Act: -0.0005

Data Index: 764205 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0552. Min Act: -0.0005

Data Index: 767013 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0564. Min Act: -0.0005

Data Index: 1348608 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0574. Min Act: -0.0005

Data Index: 358747 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0577. Min Act: -0.0005

Data Index: 1130833 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0587. Min Act: -0.0005

Data Index: 1178580 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0519. Min Act: -0.0005

Data Index: 214668 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0564. Min Act: -0.0005

Data Index: 145302 (C4 (Web Text))

Max Activating Token Index: 560