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

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

Neuron 4403 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6540. Min Act: -0.0000

Data Index: 392697 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1590063 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1634294 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5660. Min Act: -0.0000

Data Index: 1302549 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5810. Min Act: -0.0000

Data Index: 454551 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1623318 (Python Code)

Max Activating Token Index: 596

Text #6

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5704. Min Act: 0.0000

Data Index: 1562376 (Python Code)

Max Activating Token Index: 565

Text #7

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5517. Min Act: -0.0000

Data Index: 760141 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1625453 (Python Code)

Max Activating Token Index: 38

Text #9

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1403381 (Python Code)

Max Activating Token Index: 994

Text #10

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1317435 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5167. Min Act: 0.0000

Data Index: 1615092 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1117218 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5036. Min Act: -0.0000

Data Index: 972694 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1421836 (Python Code)

Max Activating Token Index: 70

Text #15

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5194. Min Act: -0.0000

Data Index: 36317 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5146. Min Act: -0.0000

Data Index: 955637 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5521. Min Act: 0.0000

Data Index: 1639416 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1364123 (Python Code)

Max Activating Token Index: 181

Text #19

Max Range: 0.6540. Min Range: -0.6540

Max Act: 0.5514. Min Act: 0.0000

Data Index: 1519621 (Python Code)

Max Activating Token Index: 100