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

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

Neuron 537 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1039750 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0002

Data Index: 894976 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0619. Min Act: -0.0002

Data Index: 83612 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1240121 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1175869 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1228430 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0608. Min Act: -0.0002

Data Index: 905063 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0596. Min Act: -0.0002

Data Index: 322642 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0591. Min Act: -0.0002

Data Index: 157121 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1231616 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1027893 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0568. Min Act: -0.0001

Data Index: 979348 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0565. Min Act: -0.0002

Data Index: 962002 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1039079 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0560. Min Act: -0.0001

Data Index: 739936 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0573. Min Act: -0.0002

Data Index: 680665 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0568. Min Act: -0.0002

Data Index: 686634 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0567. Min Act: -0.0001

Data Index: 804875 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0558. Min Act: -0.0002

Data Index: 288865 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0544. Min Act: -0.0002

Data Index: 948088 (C4 (Web Text))

Max Activating Token Index: 171