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

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

Neuron 2523 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1953. Min Act: -0.0000

Data Index: 401486 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1814. Min Act: -0.0000

Data Index: 598688 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1605. Min Act: -0.0000

Data Index: 580551 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1129741 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1638. Min Act: -0.0000

Data Index: 612734 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1575. Min Act: -0.0000

Data Index: 400597 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1569. Min Act: -0.0000

Data Index: 328498 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1598. Min Act: -0.0001

Data Index: 251262 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1473. Min Act: -0.0000

Data Index: 266776 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1655. Min Act: -0.0000

Data Index: 964770 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1420. Min Act: -0.0000

Data Index: 430404 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1075636 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1448. Min Act: -0.0000

Data Index: 461097 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1398. Min Act: -0.0000

Data Index: 419882 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1473. Min Act: -0.0000

Data Index: 809661 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1358. Min Act: -0.0000

Data Index: 170676 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1293. Min Act: -0.0000

Data Index: 315335 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1292. Min Act: -0.0000

Data Index: 465692 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1005813 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.1953. Min Range: -0.1953

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1640895 (Python Code)

Max Activating Token Index: 187