Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 440 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0627. Min Act: -0.0001

Data Index: 656529 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0001

Data Index: 357516 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1066203 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0946. Min Act: -0.0001

Data Index: 881523 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1258723 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1318147 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0530. Min Act: -0.0001

Data Index: 106808 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0458. Min Act: -0.0001

Data Index: 553588 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0563. Min Act: -0.0001

Data Index: 244462 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1077311 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0794. Min Act: -0.0001

Data Index: 30005 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0514. Min Act: -0.0001

Data Index: 418566 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1022209 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0592. Min Act: -0.0001

Data Index: 15109 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1202536 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0577. Min Act: -0.0001

Data Index: 465675 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0571. Min Act: -0.0001

Data Index: 728284 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0491. Min Act: -0.0001

Data Index: 309198 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0526. Min Act: -0.0001

Data Index: 315369 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0553. Min Act: -0.0001

Data Index: 996831 (C4 (Web Text))

Max Activating Token Index: 468