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

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

Neuron 1893 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.2361. Min Act: -0.0000

Data Index: 707253 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1935. Min Act: -0.0000

Data Index: 343631 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1722. Min Act: -0.0000

Data Index: 501913 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1745. Min Act: -0.0000

Data Index: 885294 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1797. Min Act: -0.0000

Data Index: 937739 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1005236 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1633. Min Act: -0.0000

Data Index: 710075 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1211338 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1687. Min Act: -0.0000

Data Index: 431582 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1358678 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1616. Min Act: -0.0000

Data Index: 864863 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1092774 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1307166 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1577. Min Act: -0.0000

Data Index: 83212 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1465. Min Act: -0.0000

Data Index: 48273 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1022558 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1456. Min Act: -0.0000

Data Index: 540048 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1193820 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1210109 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.2361. Min Range: -0.2361

Max Act: 0.1522. Min Act: -0.0000

Data Index: 103249 (C4 (Web Text))

Max Activating Token Index: 403