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

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

Neuron 3604 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: 0.1896. Min Range: -0.1896

Max Act: 0.1896. Min Act: -0.0000

Data Index: 922383 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1833. Min Act: -0.0000

Data Index: 629950 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1753. Min Act: -0.0000

Data Index: 671859 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1690. Min Act: -0.0000

Data Index: 49726 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1577. Min Act: -0.0000

Data Index: 207703 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1180873 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1592. Min Act: -0.0000

Data Index: 133729 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1546. Min Act: -0.0000

Data Index: 191461 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1005060 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1576. Min Act: -0.0000

Data Index: 995730 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1522. Min Act: -0.0000

Data Index: 753744 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1557. Min Act: -0.0000

Data Index: 604717 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1171704 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1310134 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1466. Min Act: -0.0000

Data Index: 732908 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1464. Min Act: -0.0000

Data Index: 103927 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1458. Min Act: -0.0000

Data Index: 514746 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1202525 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1401. Min Act: -0.0000

Data Index: 512231 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.1896. Min Range: -0.1896

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1131203 (C4 (Web Text))

Max Activating Token Index: 349