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

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

Neuron 4713 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: 0.0669. Min Range: -0.0669

Max Act: 0.0591. Min Act: -0.0002

Data Index: 755562 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0623. Min Act: -0.0002

Data Index: 931582 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0643. Min Act: -0.0002

Data Index: 413486 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0669. Min Act: -0.0002

Data Index: 841518 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0586. Min Act: -0.0002

Data Index: 584394 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0558. Min Act: -0.0002

Data Index: 720364 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0614. Min Act: -0.0002

Data Index: 588819 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0570. Min Act: -0.0002

Data Index: 12686 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0569. Min Act: -0.0002

Data Index: 702045 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0559. Min Act: -0.0002

Data Index: 336646 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0514. Min Act: -0.0002

Data Index: 189902 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0539. Min Act: -0.0002

Data Index: 915946 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0533. Min Act: -0.0002

Data Index: 29284 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0526. Min Act: -0.0002

Data Index: 568934 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0509. Min Act: -0.0002

Data Index: 546365 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0546. Min Act: -0.0002

Data Index: 496876 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1157149 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1249121 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1070051 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.0669. Min Range: -0.0669

Max Act: 0.0512. Min Act: -0.0002

Data Index: 13951 (C4 (Web Text))

Max Activating Token Index: 571