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

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

Neuron 279 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: 2.1394. Min Range: -2.1394

Max Act: 2.1394. Min Act: -0.0000

Data Index: 959799 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.7764. Min Act: -0.0000

Data Index: 1504110 (Python Code)

Max Activating Token Index: 272

Text #2

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.8472. Min Act: -0.0000

Data Index: 1450702 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.9047. Min Act: -0.0000

Data Index: 1486059 (Python Code)

Max Activating Token Index: 891

Text #4

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.8144. Min Act: -0.0000

Data Index: 1442444 (Python Code)

Max Activating Token Index: 246

Text #5

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.8996. Min Act: 0.0000

Data Index: 1157022 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.6822. Min Act: -0.0000

Data Index: 1492431 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.7356. Min Act: 0.0000

Data Index: 1436234 (Python Code)

Max Activating Token Index: 914

Text #8

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.6425. Min Act: -0.0000

Data Index: 1482691 (Python Code)

Max Activating Token Index: 661

Text #9

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.8202. Min Act: -0.0000

Data Index: 1065253 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.6327. Min Act: -0.0000

Data Index: 573162 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.6238. Min Act: -0.0000

Data Index: 1499441 (Python Code)

Max Activating Token Index: 648

Text #12

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.6138. Min Act: -0.0000

Data Index: 1465587 (Python Code)

Max Activating Token Index: 872

Text #13

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.6881. Min Act: -0.0000

Data Index: 1034006 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.5494. Min Act: 0.0000

Data Index: 1568530 (Python Code)

Max Activating Token Index: 97

Text #15

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.6293. Min Act: -0.0000

Data Index: 1414395 (Python Code)

Max Activating Token Index: 312

Text #16

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.5920. Min Act: -0.0000

Data Index: 1564876 (Python Code)

Max Activating Token Index: 388

Text #17

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.5202. Min Act: -0.0000

Data Index: 1083695 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.4976. Min Act: -0.0000

Data Index: 506135 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 2.1394. Min Range: -2.1394

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1527733 (Python Code)

Max Activating Token Index: 16