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

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

Neuron 5654 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1405233 (Python Code)

Max Activating Token Index: 713

Text #1

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1538393 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1504705 (Python Code)

Max Activating Token Index: 794

Text #3

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1495306 (Python Code)

Max Activating Token Index: 669

Text #4

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1486841 (Python Code)

Max Activating Token Index: 959

Text #5

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1491951 (Python Code)

Max Activating Token Index: 899

Text #6

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1422970 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1420276 (Python Code)

Max Activating Token Index: 836

Text #8

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6940. Min Act: -0.0000

Data Index: 1512117 (Python Code)

Max Activating Token Index: 928

Text #9

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1582804 (Python Code)

Max Activating Token Index: 503

Text #10

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1508723 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1501557 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1601740 (Python Code)

Max Activating Token Index: 880

Text #13

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1378875 (Python Code)

Max Activating Token Index: 902

Text #14

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1598823 (Python Code)

Max Activating Token Index: 206

Text #15

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1541515 (Python Code)

Max Activating Token Index: 783

Text #16

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1570989 (Python Code)

Max Activating Token Index: 351

Text #17

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1601701 (Python Code)

Max Activating Token Index: 871

Text #18

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.5898. Min Act: -0.0000

Data Index: 1560616 (Python Code)

Max Activating Token Index: 517

Text #19

Max Range: 0.8395. Min Range: -0.8395

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1500225 (Python Code)

Max Activating Token Index: 691