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

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

Neuron 3177 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2540. Min Act: -0.0000

Data Index: 175888 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2508. Min Act: -0.0000

Data Index: 838731 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1801. Min Act: -0.0000

Data Index: 829914 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1683. Min Act: -0.0000

Data Index: 30510 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1675. Min Act: -0.0000

Data Index: 799814 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1229505 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1650. Min Act: -0.0000

Data Index: 713421 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1690. Min Act: -0.0000

Data Index: 963817 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1616. Min Act: -0.0000

Data Index: 5418 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1000740 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1551. Min Act: -0.0000

Data Index: 806746 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1585. Min Act: -0.0000

Data Index: 26611 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1624. Min Act: -0.0000

Data Index: 68998 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1520. Min Act: -0.0000

Data Index: 309888 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1012196 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1489. Min Act: -0.0000

Data Index: 369615 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1494. Min Act: -0.0000

Data Index: 704129 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1520. Min Act: -0.0000

Data Index: 991228 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1522. Min Act: -0.0000

Data Index: 363374 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1517. Min Act: -0.0000

Data Index: 692357 (C4 (Web Text))

Max Activating Token Index: 280