Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3003 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1612. Min Range: -5.1612

Max Act: 5.0226. Min Act: -0.0000

Data Index: 1507682 (Python Code)

Max Activating Token Index: 82

Text #1

Max Range: 5.1612. Min Range: -5.1612

Max Act: 5.1612. Min Act: -0.0000

Data Index: 1431808 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.6034. Min Act: -0.0000

Data Index: 1380316 (Python Code)

Max Activating Token Index: 472

Text #3

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.5904. Min Act: -0.0000

Data Index: 1505318 (Python Code)

Max Activating Token Index: 869

Text #4

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.2622. Min Act: -0.0000

Data Index: 1561800 (Python Code)

Max Activating Token Index: 909

Text #5

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.6140. Min Act: -0.0000

Data Index: 1469330 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.3802. Min Act: -0.0000

Data Index: 1599892 (Python Code)

Max Activating Token Index: 383

Text #7

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.0553. Min Act: -0.0000

Data Index: 1438242 (Python Code)

Max Activating Token Index: 823

Text #8

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.0368. Min Act: -0.0000

Data Index: 1509402 (Python Code)

Max Activating Token Index: 915

Text #9

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.5621. Min Act: -0.0000

Data Index: 1584883 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.1427. Min Act: -0.0000

Data Index: 1607154 (Python Code)

Max Activating Token Index: 460

Text #11

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.4393. Min Act: -0.0000

Data Index: 1476697 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.4735. Min Act: -0.0000

Data Index: 1580424 (Python Code)

Max Activating Token Index: 353

Text #13

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.0251. Min Act: -0.0000

Data Index: 1600687 (Python Code)

Max Activating Token Index: 691

Text #14

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.0988. Min Act: -0.0000

Data Index: 1520539 (Python Code)

Max Activating Token Index: 666

Text #15

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.2571. Min Act: -0.0000

Data Index: 1554180 (Python Code)

Max Activating Token Index: 654

Text #16

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.1032. Min Act: -0.0000

Data Index: 1524992 (Python Code)

Max Activating Token Index: 559

Text #17

Max Range: 5.1612. Min Range: -5.1612

Max Act: 3.9301. Min Act: -0.0000

Data Index: 1540010 (Python Code)

Max Activating Token Index: 207

Text #18

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.2179. Min Act: -0.0000

Data Index: 1472128 (Python Code)

Max Activating Token Index: 658

Text #19

Max Range: 5.1612. Min Range: -5.1612

Max Act: 4.0608. Min Act: -0.0000

Data Index: 1508041 (Python Code)

Max Activating Token Index: 530